From 48b5e758b9f66fe0e36a6c28189adaf3ec517fd3 Mon Sep 17 00:00:00 2001 From: "W. Trevor King" Date: Tue, 24 Aug 2010 12:54:53 -0400 Subject: [PATCH] Convert ChemDB from web.py to CherryPy. I like CherryPy's interface better, and web.py depends on CherryPy anyway. Time to cut out the middleman. Also moved to a non-flat directory structure. This was a major reorganization, so it may have introduced a few bugs. I'll probably turn up anything major in the next day or two. I've learned a lot about Python since I wrote the earlier versions of ChemDB. The portions that I've rewritten reflect those changes, but a good of the unchanged code is still a bit awkward. Still to come: * Remove metapost dependency by using PGF/TikZ to generate the NFPA diamond. --- .gitignore | 38 +- COPYING | 674 ++++++++++++++++++ DEPENDENCIES | 68 +- README | 131 ++-- bin/chem_db.py | 225 ++++++ bin/chem_web.py | 9 + chem_db.py | 541 -------------- chem_web.py | 587 --------------- chemdb/__init__.py | 1 + chemdb/chemdb.py | 379 ++++++++++ daemon.py => chemdb/daemon.py | 0 chemdb/db/__init__.py | 1 + text_db.py => chemdb/db/text.py | 489 +++++++------ chemdb/server.py | 372 ++++++++++ certgen.py => contrib/ssl/certgen.py | 0 .../ssl/mk_simple_certs.py | 10 +- {examples => example}/inventory.db | 0 example/static/MSDS/0.html | 7 + {docs => template/doc}/Makefile | 0 {docs => template/doc}/README | 0 {docs => template/doc}/contact.tex | 0 {docs => template/doc}/door_template.tex | 0 {docs => template/doc}/inventory_template.tex | 0 {docs => template/doc}/mp/Makefile | 0 {docs => template/doc}/mp/NFPA_c.mp | 0 {docs => template/doc}/mp/README | 0 {docs => template/doc}/mp/gen_NFPA.sh | 0 {docs => template/doc}/mp/sample.tex | 0 template/web/base.html | 34 + template/web/docs.html | 35 + template/web/edit-record.html | 58 ++ template/web/index.html | 39 + template/web/record.html | 26 + update_copyright.py | 621 ++++++++++++++++ 34 files changed, 2852 insertions(+), 1493 deletions(-) create mode 100644 COPYING create mode 100755 bin/chem_db.py create mode 100755 bin/chem_web.py delete mode 100755 chem_db.py delete mode 100755 chem_web.py create mode 100644 chemdb/__init__.py create mode 100644 chemdb/chemdb.py rename daemon.py => chemdb/daemon.py (100%) create mode 100644 chemdb/db/__init__.py rename text_db.py => chemdb/db/text.py (58%) create mode 100644 chemdb/server.py rename certgen.py => contrib/ssl/certgen.py (100%) rename mk_simple_certs.py => contrib/ssl/mk_simple_certs.py (77%) mode change 100644 => 100755 rename {examples => example}/inventory.db (100%) create mode 100644 example/static/MSDS/0.html rename {docs => template/doc}/Makefile (100%) rename {docs => template/doc}/README (100%) rename {docs => template/doc}/contact.tex (100%) rename {docs => template/doc}/door_template.tex (100%) rename {docs => template/doc}/inventory_template.tex (100%) rename {docs => template/doc}/mp/Makefile (100%) rename {docs => template/doc}/mp/NFPA_c.mp (100%) rename {docs => template/doc}/mp/README (100%) rename {docs => template/doc}/mp/gen_NFPA.sh (100%) rename {docs => template/doc}/mp/sample.tex (100%) create mode 100644 template/web/base.html create mode 100644 template/web/docs.html create mode 100644 template/web/edit-record.html create mode 100644 template/web/index.html create mode 100644 template/web/record.html create mode 100755 update_copyright.py diff --git a/.gitignore b/.gitignore index f0ee07f..7b798e3 100644 --- a/.gitignore +++ b/.gitignore @@ -1,35 +1,3 @@ -MSDS -backup -certgen.pyc -chem_db.pyc -chem_web.log -chem_web.log.1 -chem_web.log.2 -chem_web.log.3 -chem_web.log.4 -chem_web.log.5 -chem_web.pid -chem_web.pyc -current -daemon.pyc -docs/door_data.tex -docs/door_warning.pdf -docs/inventory_data.tex -docs/inventory.pdf -docs/main.aux -docs/main.log -docs/main.pdf -docs/main.tex -docs/mp/NFPA.1 -docs/mp/NFPA.log -docs/mp/NFPA.mp -docs/mp/NFPA.mpx -docs/mp/sample.aux -docs/mp/sample.log -docs/mp/sample.pdf -mk_simple_certs.pyc -origs -restart.sh -ssl -templates -text_db.pyc +*.pyc +chem_web.log* +backup/ diff --git a/COPYING b/COPYING new file mode 100644 index 0000000..94a9ed0 --- /dev/null +++ b/COPYING @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. diff --git a/DEPENDENCIES b/DEPENDENCIES index b03675b..18fab04 100644 --- a/DEPENDENCIES +++ b/DEPENDENCIES @@ -1,45 +1,33 @@ -------------------------------Python dependencies------------------------------ +Python dependencies +=================== -STANDARD MODULES +Standard modules +---------------- -Modules included with a standard Python 2.5 distribution: +Modules included with a standard Python 2.6 distribution: Documentation available at - http://docs.python.org/lib/module-.html - -copy -doctest -logging -optparse -os -os.path -re -shutil -stat -string -sys -time -types - - -EXTERNAL MODULES - -OpenSSL http://pyopenssl.sourceforge.net/ - Python wrapper on OpenSSL library. -web http://webpy.org/ - A simple web framework. I think the Debain package was too - old a version. I installed mine from source, version 0.23. - Patched httpserver.py to support HTTPS. - Patch submitted upstream: - https://bugs.launchpad.net/webpy/+bug/262495 -markdown Implements a version of markdown syntax. webpy bundles a - version of this in their `tools' subdirectory. - -------------------------------System dependencies------------------------------ - -You need latex and metapost to compile the documents. The -texlive-base, texlive-metapost, and context Debian packages should -cover you. You can avoid the context dependency with some legwork, -see - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=465107 + http://docs.python.org/library/.html +External modules +---------------- +* `OpenSSL`_, a Python wrapper on OpenSSL library. +* `CherryPy`_, a simple web framework. +* `Jinja2`_, a template engine. + +.. _OpenSSL: http://pyopenssl.sourceforge.net/ +.. _CherryPy: http://www.cherrypy.org/ +.. _Jinja2: http://jinja.pocoo.org/2/ + +System dependencies +=================== + +You need `LaTeX`_ and `MetaPost`_ to compile the documents. The +`texlive-base`, `texlive-metapost`, and `context` `Debian`_ packages +should cover you. You can avoid the context dependency with some +`legwork`_. + +.. _LaTeX: http://www.latex-project.org/ +.. _MetaPost: http://tug.org/metapost.html +.. _Debian: http://www.debian.org/ +.. _legwork: http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=465107 diff --git a/README b/README index 524bdeb..0fb04db 100644 --- a/README +++ b/README @@ -1,42 +1,48 @@ Web, python, and command-line interfaces for managing a chemical inventory. -COMMANDS +Commands +======== The web interface (chem_web.py) is a web-daemon using web.py and it's build in htmlserver. -Standard command for starting the daemon - $ chem_web.py -a 192.168.1.2:55555 -Standard command for stopping the daemon - $ chem_web.py --stop +Standard command for starting the daemon:: -From the command line, you can validate CAS#s (and possibly other fields) with - $ python chem_db.py -f current/inventory.db -V + $ chem_web.py -a 192.168.1.2:55555 +Standard command for stopping the daemon:: -DATABASE FORMAT + $ chem_web.py --stop + +From the command line, you can validate CAS#s (and possibly other fields) with:: + + $ python chem_db.py -f current/inventory.db -V + + +Database format +=============== text_db.py provides the python interface to this format. The basic idea was to produce and use files which were M$-Excel-compatible, since future users might not want to maintain this interface. A brief example inventory.db file is included in the examples directory. -Tab-delimited ('\t') fields -Endline-delimited ('\n') records -The first line is the header (starts with a pound sign '#'). -The header should be a tab-delimited list of short field names. -If the second line also begins with a pound sign, -it contains a tab-delimiteded list of long field names. -Blank lines are ignored. +* Tab-delimited ('\t') fields +* Endline-delimited ('\n') records +* The first line is the header (starts with a pound sign '#'). +* The header should be a tab-delimited list of short field names. +* If the second line also begins with a pound sign, + it contains a tab-delimiteded list of long field names. +* Blank lines are ignored. The fields H, F, R, and S are the NFPA Health, Fire, Reactivity, and Special Hazards (NFPA diamond). -Blue: Health Hazard +* Blue: Health Hazard 0 Hazard no greater than ordinary material 1 May cause irritation; minimal residual injury 2 Intense or prolonged exposure may cause incapacitation; Residual injury may occur if not treated 3 Exposure could cause serious injury even if treated 4 Exposure may cause death -Red: Fire Hazard +* Red: Fire Hazard 0 Will not burn 1 Must be preheated for ignition; flashpoint above 200°F (93°C) 2 Must be moderately heated for ignition, flashpoint above 100°F (38°C) @@ -44,7 +50,7 @@ Red: Fire Hazard Flashpoint below 100°F (38°C) 4 Extremely flammable and will readily disperse through air under standard conditions, flashpoint below 73°F (23°C) -Reactivity hazards: +* Reactivity hazards: 0 Stable 1 May become unstable at elevated temperatures and pressures. May be mildly water reactive @@ -52,60 +58,71 @@ Reactivity hazards: May form explosive mixtures with water 3 Detonates with strong ignition source 4 Readily detonates -Special Hazards have the following codes: - OX strong oxidizer - -W- water reactive - SA simple ascphyxiants - (The only gases for which this symbol is permitted are nitrogen, helium, - neon, argon, krypton, and xenon..) -Non-official Special Hazard codes: - ACID acid - ALK base - COR corrosive - BIO Biohazard - POI Poison - CRY Cyrogenic - - -CONTENTS - -README this file -text_db.py python interface to the above db format -chem_db.py chem-inventory specific functionality such as - * CAS # validation, +* Special Hazards have the following codes: + * OX strong oxidizer + * -W- water reactive + * SA simple ascphyxiants + (The only gases for which this symbol is permitted are nitrogen, helium, + neon, argon, krypton, and xenon..) +* Unofficial Special Hazard codes: + * ACID acid + * ALK base + * COR corrosive + * BIO Biohazard + * POI Poison + * CRY Cyrogenic + + +Contents +======== + +* README this file +* DEPENDENCIES list of dependencies (libraries, python modules, etc.) +* COPYING GNU General Public License, version 3 +* text_db.py python interface to the above db format +* chem_db.py chem-inventory specific functionality such as + * CAS # validation, * a Material Saftey Data Sheet (MSDS) manager, - * document-generation drivers, and - * a simple command line interface. -current store the current database file. -backup store previous (timestamped) database files. - You may want to clean this out occasionally. -MSDS store Material Saftey Data Sheets by database index number -docs latex (and metapost) sources for document generation. -chem_web.py daemonized web bindings to chem_web.py -ssl Secure Socket Layer (SSL) key and certificate generation tests. + * document-generation drivers, and + * a simple command line interface. +* current store the current database file. +* backup store previous (timestamped) database files. + You may want to clean this out occasionally. +* MSDS store Material Saftey Data Sheets by database index number +* docs latex (and metapost) sources for document generation. +* chem_web.py daemonized web bindings to chem_web.py +* ssl Secure Socket Layer (SSL) key and certificate generation tests. -GENERATED FILES AND DIRECTORIES +Generated files and directories +------------------------------- +============ ======================================================================= templates quasi-HTML templates for pages generated chem_web.py chem_web.pid store the Process ID (PID) for a daemonized chem_web.py process chem_web.log log chem_web activity (maintained between runs, so remove periodically) - +============ ======================================================================= TODO +==== -Security: +Security +-------- I can create my own self-signed certificate. Protects against eavesdropping, but not man-in-the-middle attacks. Solution for now: hide from external world, trust everyone inside, backup before any change. -Print columns in a particular order from the database with - $ awk -F ' ' '{print $1, "\t", $9, "\t", , "\t", $2}' current/inventory.db | less +History +======= + +The original web fron-end was based on Adam Bachman's simplewiki.py_. + +.. simplewiki.py: http://bachman.infogami.com/another_simple_wiki -HISTORY +License +======= -The web front-end on this database is an adaptation of Adam Bachman's -simplewiki.py - http://bachman.infogami.com/another_simple_wiki +ChemDB is released under the GNU General Public License version 3. +See :file:`COPYING` for details. diff --git a/bin/chem_db.py b/bin/chem_db.py new file mode 100755 index 0000000..9c9c4ba --- /dev/null +++ b/bin/chem_db.py @@ -0,0 +1,225 @@ +#!/usr/bin/python + +# Copyright + +from sys import stdout, stdin, stderr + +import chemdb.chemdb + +from chemdb.db.text import TextDB, DBPrettyPrinter + + +def open_IOfiles(ifilename=None, ofilename=None, debug=False): + if ifilename: + if debug: print >> stderr, "open input file '%s'" % ifilename + ifile = file(ifilename, 'r') + else: + ifile = stdin + if ofilename: + if debug: print >> stderr, "open output file '%s'" % ofilename + ofile = file(ofilename, 'w') + else: + ofile = stdout + return (ifile, ofile) + +def close_IOfiles(ifilename=None, ifile=stdin, + ofilename=None, ofile=stdout, + debug=False): + if ifilename: + if debug: print >> stderr, "close input file '%s'" % ifilename + ifile.close() + if ofilename: + if debug: print >> stderr, "close output file '%s'" % ofilename + ofile.close() + +if __name__ == '__main__': + from optparse import OptionParser + + parser = OptionParser(usage='usage: %prog [options]', version='%prog 0.1') + + parser.add_option('-f', '--input-file', dest='ifilename', + help='Read input from FILE (default stdin)', + type='string', metavar='FILE') + parser.add_option('-o', '--output-file', dest='ofilename', + help='Write output to FILE (default stdout)', + type='string', metavar='FILE') + parser.add_option('-d', '--delimiter', dest='FS', # field seperator + help="Set field delimiter (default '%default')", + type='string', metavar='DELIM', default='\t') + parser.add_option('-p', '--print-fields', dest='print_fields', + help='Only print certain fields (e.g. 0,3,4,2)', + type='string', metavar='FIELDS') + parser.add_option('-r', '--print-records', dest='print_records', + help='Only print certain records (e.g. 0:3)', + type='string', metavar='RECORDS') + parser.add_option('-w', '--column-width', dest='width', + help='Set column width for short-format output.', + type='string', metavar='WIDTH') + parser.add_option('-L', '--long-format', dest='long_format', + help='Print long format (several lines per record)', + action='store_true', default=False) + parser.add_option('-l', '--short-format', dest='long_format', + help='Print short format (default) (one lines per record)', + action='store_false', default=False) + parser.add_option('--valid-record', dest='valid_record', + help="Select fields where True == lambda r : eval(EXPRESSION). default '%default'", + type='string', metavar='EXPRESSION', default="r['Disposed'] == ''") + parser.add_option('--sort-field', dest='sort_field', + help="Sort matching records by FIELD (defauly '%default')", + type='string', metavar='FIELD', default='db_id') + parser.add_option('--pdf-title', dest='pdf_title', + help='Override the default PDF title', + type='string', metavar='TITLE') + parser.add_option('--inventory', dest='inventory', + help='Output a PDF inventory of matching records', + action='store_true', default=False) + parser.add_option('--door-warning', dest='door_warning', + help='Output a PDF door warning of matching records', + action='store_true', default=False) + parser.add_option('-t', '--test', dest='test', + help='Run docutils tests on db.py', + action='store_true', default=False) + parser.add_option('--list-locations', dest='locations', + help='List all currently used locations (no other output)', + action='store_true', default=False) + parser.add_option('-V', '--validate', dest='validate', + help='Validate CAS#s (no other output)', + action='store_true', default=False) + parser.add_option('-A', '--audit', dest='audit', + help='Search for troublesome entries (no other output)', + action='store_true', default=False) + parser.add_option('-v', '--verbose', dest='verbose', + help='Print lots of debugging information', + action='store_true', default=False) + + (options, args) = parser.parse_args() + parser.destroy() + + ifile,ofile = open_IOfiles(options.ifilename, options.ofilename, + options.verbose) + + if options.test: + _test() + elif options.locations: + db = TextDB(filename=None) + pp = DBPrettyPrinter(db) + + # read in and parse the file + db._parse(ifile.read()) + + locations = [] + for record in db.records(): + if len(record['Location']) > 0 and record['Location'] not in locations: + locations.append(record['Location']) + locations.sort() + print >> ofile, '\n'.join(locations) + elif options.validate: + db = TextDB(filename=None) + pp = DBPrettyPrinter(db) + + # read in and parse the file + db._parse(ifile.read()) + + CAS_DELIM = ',' # seperate CAS entries for chemicals with multiple CAS numbers + PERCENT_DELIM = ':' # seperate CAS number from ingredient percentage + for record in db.records(): + valid = True + cas = record['CAS#'] + if len(cas.split(CAS_DELIM)) == 0 : # cas = 'N...N-NN-N' + if not valid_CASno(cas, options.verbose): + valid = False + print >> ofile, "Invalid CAS# in record: '%s'" % cas + else : # cas = 'N...N-NN-N:X%,N...N-NN-N:Y%,...' + for casterm in cas.split(CAS_DELIM) : # casterm = 'N...N-NN-N:X%' + c = casterm.split(PERCENT_DELIM)[0] # c = 'N...N-NN-N' + if not valid_CASno(c, options.verbose): + valid = False + print >> ofile, "Invalid CAS* in record: '%s'" % c + if not valid: + print >> ofile, ( + "in record %s: %s" % (record['ID'], record['Name'])) + #pp.full_record_string(record) + elif options.audit: + db = TextDB(filename=None) + pp = DBPrettyPrinter(db) + + # read in and parse the file + db._parse(ifile.read()) + + for record in db.records(): + # check for extra spaces + for key,value in record.items(): + if (isinstance(value, types.StringTypes) + and value.strip() != value): + print >> ofile, ( + "Extra whitespace for %s - %s field %s : '%s'" + % (record['ID'], record['Name'], key, value)) + # make sure we know the location of all current chemicals + if len(record['Disposed']) == 0 and len(record['Location']) == 0: + print >> ofile, ( + "Misplaced record: %s - %s" + % (record['ID'], record['Name'])) + elif options.inventory: + db = TextDB(filename=None) + pp = DBPrettyPrinter(db) + + # read in and parse the file + db._parse(ifile.read()) + + dgen = docgen(db) + def valid_record(r): + return eval(options.valid_record, # expression + {'__builtins__':None}, # globals + {'r':r}) # locals + path = dgen.inventory(title=options.pdf_title, + namewidth=40, + sort_field=options.sort_field, + valid_record=valid_record) + print >> ofile, '\n', path + elif options.door_warning: + db = TextDB(filename=None) + pp = DBPrettyPrinter(db) + + # read in and parse the file + db._parse(ifile.read()) + + dgen = docgen(db) + def valid_record(r): + return eval(options.valid_record, # expression + {'__builtins__':None}, # globals + {'r':r}) # locals + path = dgen.door_warning(valid_record=valid_record) + print >> ofile, '\n', path + else: + db = TextDB(filename=None) + + # read in and parse the file + db._parse(ifile.read()) + pp = DBPrettyPrinter(db) + if options.long_format: + for id in pp._norm_record_ids(options.print_records): + string = pp.full_record_string_id(id) + else: + # pythonize the width option + if options.width == None or options.width == 'a': + width = options.width + elif len(options.width.split(':')) == 1: + width = int(options.width) + elif len(options.width.split(':')) > 1: + width = {} + for kv in options.width.split(','): + spl = kv.split(':') + assert len(spl) == 2, 'invalid width "%s" in "%s"' % (kv, options.width) + if spl[1] == 'a': + width[spl[0]] = spl[1] + else: + width[spl[0]] = int(spl[1]) + + string = pp.multi_record_string(options.print_records, + options.print_fields, + width, + options.FS) + print >> ofile, string, + + close_IOfiles(options.ifilename, ifile, + options.ofilename, ofile, options.verbose) diff --git a/bin/chem_web.py b/bin/chem_web.py new file mode 100755 index 0000000..89ba099 --- /dev/null +++ b/bin/chem_web.py @@ -0,0 +1,9 @@ +#!/usr/bin/python + +# Copyright + +from chemdb.server import ServerDaemon + + +if __name__=="__main__": + ServerDaemon().main() diff --git a/chem_db.py b/chem_db.py deleted file mode 100755 index 7d74ca7..0000000 --- a/chem_db.py +++ /dev/null @@ -1,541 +0,0 @@ -#!/usr/bin/python - -""" -Extend text_db with a CAS# validator, a command line interface, and document generation. -""" - -from text_db import * -import re -import os -import os.path -import time -import types - -def valid_CASno(cas_string, debug=False): - """ - Check N..NN-NN-N format, and the checksum digit for valid CAS number structure. - see http://www.cas.org/expertise/cascontent/registry/checkdig.html - for N_n .. N_4 N_3 - N_2 N_1 - R - R = remainder([sum_{i=1}^n i N_i ] / 10 ) - Ignores 'na' and '+secret-non-hazardous' - >>> valid_CASno('107-07-3') - True - >>> valid_CASno('107-08-3') - False - >>> valid_CASno('107-083') - False - """ - for string in ['na', '+secret-non-hazardous']: - # the first marks a non-existent CAS# - # the last marks items with secret, non-hazardous ingredients for which we have no CAS# - if cas_string == string: - return True - # check format, - # ^ matches the start of the string - # \Z matches the end of the string - regexp = re.compile('^[0-9]{2,}[-][0-9]{2}[-][0-9]\Z') - if regexp.match(cas_string) == None: - if debug : print >> stderr, "invalid CAS# format: '%s'" % cas_string - return False - # generate check digit - casdigs = "".join(cas_string.split('-')) # remove '-' - sumdigs = list(casdigs[:-1]) - sumdigs.reverse() - sum=0 - for i in range(len(sumdigs)) : - sum += (i+1)*int(sumdigs[i]) - check = sum % 10 - if int(casdigs[-1]) == check : - return True - else : - if debug : print >> stderr, "invalid CAS# check: '%s' (expected %d)" % (cas_string, check) - return False - -class MSDS_manager (object) : - """ - Manage Material Saftey Data Sheets (MSDSs) - """ - def __init__(self, db, dir="./MSDS/") : - self.db = db - self.dir = dir - self.MIMEs = ['application/pdf', - 'text/html', - 'text/plain'] - self.MIME_exts = ['pdf', 'html', 'txt'] - self.check_dir() - def check_dir(self) : - "Create the MSDS directory if it's missing" - if os.path.isdir(self.dir) : - return # all set to go - elif os.path.exists(self.dir) : - raise Exception, "Error: a non-directory file exists at %s" % self.dir - else : - os.mkdir(self.dir) - def basepath(self, id) : - assert type(id) == types.IntType, 'id must be an integer, not %s (%s)' \ - % (type(id), str(id)) - return os.path.join(self.dir, "%d" % id) - def local_basepath(self, id) : # for symbolic links - assert type(id) == types.IntType, 'id must be an integer, not %s (%s)' \ - % (type(id), str(id)) - return "./%d" % id - def MIME_ext(self, mime) : - assert mime in self.MIMEs, \ - "invalid MIME type '%s'\nshould be one of %s" % (mime, self.MIMEs) - i = self.MIMEs.index(mime) - ext = self.MIME_exts[i] - return ext - def path(self, id, mime) : - return "%s.%s" % (self.basepath(id), self.MIME_ext(mime)) - def local_path(self, id, mime) : - return "%s.%s" % (self.local_basepath(id), self.MIME_ext(mime)) - def save(self, id, filetext, mime='application/pdf') : - "Save the binary byte string FILE to the path for ID" - print >> file(self.path(id, mime), 'wb'), filetext, - def link(self, id, target_id) : - # target_id already exists, create a symlink to it for id. - target_mime = self.get_MSDS_MIME(target_id) - target_path = self.local_path(target_id, target_mime) - path = self.path(id, target_mime) - #os.link(self.path(target_id), self.path(id)) # hard link... - os.symlink(target_path, path) # ... or soft link - def has_MSDS_MIME(self, id, mime) : - """ - >>> m = MSDS_manager(db=None) - >>> print m.has_MSDS_type(102, 'pdf') # test on html - False - >>> print m.has_MSDS_type(102, 'html') # test on html - True - >>> print m.has_MSDS_type(6, 'pdf') # test on pdf symlink - True - """ - return os.path.exists(self.path(id, mime)) - def get_MSDS_path(self, id) : - """ - >>> m = MSDS_manager(db=None) - >>> print m.get_MSDS_path(102) # test on html - ./MSDS/102.html - >>> print m.get_MSDS_path(1) # test on pdf - ./MSDS/1.pdf - >>> print m.get_MSDS_path(6) # test on pdf symlink - ./MSDS/6.pdf - """ - for mime in self.MIMEs : - if self.has_MSDS_MIME(id, mime) : - return self.path(id, mime) - return None - def get_MSDS_MIME(self, id) : - """ - >>> m = MSDS_manager(db=None) - >>> print m.get_MSDS_MIME(102) # test on html - text/html - >>> print m.get_MSDS_MIME(1) # test on pdf - application/pdf - >>> print m.get_MSDS_MIME(6) # test on pdf symlink - application/pdf - """ - for mime in self.MIMEs : - if self.has_MSDS_MIME(id, mime) : - return mime - return None - def has_MSDS(self, id) : - if self.get_MSDS_path(id) == None : - return False - return True - def get_all(self, simlinks=True) : - ret = [] - for record in self.db.records() : - p = self.get_MSDS_path( int(record['ID']) ) - if p != None : - if simlinks == False and os.path.islink( p ) : - continue # ignore the symbolic link - ret.append({'ID':record['ID'], 'Name':record['Name']}) - return ret - -class docgen (object) : - "Generate the officially required documents" - def __init__(self, db) : - self.db = db - def _latex_safe(self, string): - string = string.replace('%', '\%') - string = string.replace('>', '$>$') - string = string.replace('<', '$<$') - return string - def _set_main_target(self, target): - print >> file('./docs/main.tex', 'w'), \ - """\documentclass[letterpaper]{article} - -\input{%s} -""" % target - def _make_pdf(self, target_file): - os.system('cd ./docs && make pdf') - path = os.path.join('./docs/', target_file) - os.system('cp ./docs/main.pdf %s' % path) - return path - def inventory(self, title=None, - namewidth='a', sort_field='db_id', - valid_record=lambda r: r['Disposed'] == '') : - """Create a pdf list of all maching chemicals. The default is to - match all currently owned chemicals. Matching chemicals can be sorted - by any field (defaults to 'ID').""" - if title == None: - title == 'Inventory' - pp = db_pretty_printer(self.db) - active_ids = [] - for record in self.db.records() : - if valid_record(record) : # get ids for matching chemicals - active_ids.append(record['db_id']) - active_ids.sort(cmp=lambda a,b: cmp(self.db.record(a)[sort_field], - self.db.record(b)[sort_field])) - active_fields = ['ID', 'Name', 'Amount', - 'H', 'F', 'R', 'O', 'M', 'C', 'T'] - width = {} - for field in active_fields : - width[field] = 'a' - width['Name'] = namewidth - ## Plain text method - #string = "Chemical inventory:\t\tGenerated on %s\n\n" \ - # % time.strftime('%Y-%m-%d') - #string += pp.multi_record_string(active_ids, active_fields, - # width=width, FS=' ') - # return string - ## Latex method - string = "\\begin{longtable}{l l l c c c c c c c}\n" - string += ('%% The header for the remaining page(s) of the table...\n' - 'ID & Name & Amount & H & F & R & O & M & C & T \\\\\n' - '\\hline\n' - '\\endhead\n') - for db_id in active_ids : - record = self.db.record(db_id) - string += " %s & %s & %s & %s & %s & %s & %s & %s & %s & %s \\\\\n" \ - % (self._latex_safe(record['ID']), - self._latex_safe(record['Name']), - self._latex_safe(record['Amount']), - self._latex_safe(record['H']), - self._latex_safe(record['F']), - self._latex_safe(record['R']), - self._latex_safe(record['O']), - self._latex_safe(record['M']), - self._latex_safe(record['C']), - self._latex_safe(record['T'])) - string += "\\end{longtable}\n" - print >> file('./docs/inventory_title.tex', 'w'), title - print >> file('./docs/inventory_data.tex', 'w'), string - ## alter main.tex to point to the inventory template. - self._set_main_target('inventory_template') - ## run latex - path = self._make_pdf('inventory.pdf') - return path - def door_warning(self, - valid_record=lambda r: r['Disposed'] == '') : - """create a warning NFPA diamond and list of the most dangerous - chemicals for which valid_record(record) is true. For - example, to generate a door warning for the front door use - door_warning(lambda r: r['Disposed'] == '') - or to generate the warning for the fridge - door_warning(lambda r: r['Location'] == 'Refrigerator') - Note that valid_record defaults to the first example. - """ - pp = db_pretty_printer(self.db) - all_ids = range(self.db.len_records()) - - # Search the database to find the nasties - NFPA_maxs = {'H':0, 'F':0, 'R':0, 'O':[]} - Mutagens = [] - Carcinogens = [] - Teratogens = [] - Healths = [] - Fires = [] - Reactivities = [] - Others = [] - for record in self.db.records() : - if valid_record(record) : - for field in ['H', 'F', 'R', 'O'] : - r = record[field] - if r != '' and r != '?' : - if field != 'O' and int(r) > NFPA_maxs[field] : - NFPA_maxs[field] = int(r) - elif field == 'O' and not r in NFPA_maxs['O'] : - NFPA_maxs[field].append(r) - for field,array in zip(['M','C','T'], - [Mutagens, - Carcinogens, - Teratogens]) : - if record[field] != '' and record[field] != '?': - array.append(record['db_id']) - # now that we've found the max NFPAs, - # find all the chemicals at those levels - for record in self.db.records() : - if valid_record(record) : - for field,array in zip(['H', 'F', 'R', 'O'], - [Healths, Fires, - Reactivities, Others]) : - r = record[field] - if r != '' and r != '?' : - if field != 'O' and int(r) == NFPA_maxs[field] : - array.append(record['db_id']) - elif field == 'O' and r in NFPA_maxs['O'] : - array.append(record['db_id']) - - ## generate the output - # first, update the NFPA grapic code - if 'OX' in NFPA_maxs['O'] : OX = 'y' - else : OX = 'n' - if 'W' in NFPA_maxs['O'] : W = 'y' - else : W = 'n' - os.system('./docs/mp/gen_NFPA.sh %d %d %d %s %s > ./docs/mp/NFPA.mp' - % (NFPA_maxs['H'], NFPA_maxs['F'], NFPA_maxs['R'], OX, W)) - # now generate a list of the nasties ( Amount & ID & Name ) - string = "\\begin{tabular}{r r l}\n" - for field,name,array in zip(['H', 'F', 'R', 'O'], - ['Health', 'Fire', - 'Reactivity', 'Other'], - [Healths, Fires, - Reactivities, Others]) : - if (not hasattr(NFPA_maxs[field], '__len__')) \ - or len(NFPA_maxs[field]) > 0 : - string += " \multicolumn{3}{c}{\Tstrut %s : %s} \\\\\n" \ - % (name, NFPA_maxs[field]) - else : # Print "Other" instead of "Other : []" - string += " \multicolumn{3}{c}{\Tstrut %s} \\\\\n" \ - % (name) - for db_id in array : - record = self.db.record(db_id) - string += " %s & %s & %s \\\\\n" \ - % (self._latex_safe(record['Amount']), - self._latex_safe(record['ID']), - self._latex_safe(record['Name'])) - if len(array) == 0 : - string += " \multicolumn{3}{c}{ --- } \\\\\n" - for hazard,array in zip(['Mutagens','Carcinogens','Teratogens'], - [Mutagens, Carcinogens, Teratogens]) : - string += " \multicolumn{3}{c}{\Tstrut %s} \\\\\n" % (hazard) - for db_id in array : - record = self.db.record(db_id) - string += " %s & %s & %s \\\\\n" \ - % (self._latex_safe(record['Amount']), - self._latex_safe(record['ID']), - self._latex_safe(record['Name'])) - if len(array) == 0 : - string += " \multicolumn{3}{c}{ --- } \\\\\n" - string += "\\end{tabular}\n" - print >> file('./docs/door_data.tex', 'w'), string - ## alter main.tex to point to the door template. - self._set_main_target('door_template') - ## run latex - path = self._make_pdf('door_warning.pdf') - return path - -def _test(): - import doctest - doctest.testmod() - -def open_IOfiles(ifilename=None, ofilename=None, debug=False): - if ifilename : - if debug : print >> stderr, "open input file '%s'" % ifilename - ifile = file(ifilename, 'r') - else : - ifile = stdin - if ofilename : - if debug : print >> stderr, "open output file '%s'" % ofilename - ofile = file(ofilename, 'w') - else : - ofile = stdout - return (ifile, ofile) - -def close_IOfiles(ifilename=None, ifile=stdin, - ofilename=None, ofile=stdout, - debug=False): - if ifilename : - if debug : print >> stderr, "close input file '%s'" % ifilename - ifile.close() - if ofilename : - if debug : print >> stderr, "close output file '%s'" % ofilename - ofile.close() - - -if __name__ == '__main__' : - from optparse import OptionParser - - parser = OptionParser(usage='usage: %prog [options]', version='%prog 0.1') - - parser.add_option('-f', '--input-file', dest='ifilename', - help='Read input from FILE (default stdin)', - type='string', metavar='FILE') - parser.add_option('-o', '--output-file', dest='ofilename', - help='Write output to FILE (default stdout)', - type='string', metavar='FILE') - parser.add_option('-d', '--delimiter', dest='FS', # field seperator - help="Set field delimiter (default '%default')", - type='string', metavar='DELIM', default='\t') - parser.add_option('-p', '--print-fields', dest='print_fields', - help='Only print certain fields (e.g. 0,3,4,2)', - type='string', metavar='FIELDS') - parser.add_option('-r', '--print-records', dest='print_records', - help='Only print certain records (e.g. 0:3)', - type='string', metavar='RECORDS') - parser.add_option('-w', '--column-width', dest='width', - help='Set column width for short-format output.', - type='string', metavar='WIDTH') - parser.add_option('-L', '--long-format', dest='long_format', - help='Print long format (several lines per record)', - action='store_true', default=False) - parser.add_option('-l', '--short-format', dest='long_format', - help='Print short format (default) (one lines per record)', - action='store_false', default=False) - parser.add_option('--valid-record', dest='valid_record', - help="Select fields where True == lambda r : eval(EXPRESSION). default '%default'", - type='string', metavar='EXPRESSION', default="r['Disposed'] == ''") - parser.add_option('--sort-field', dest='sort_field', - help="Sort matching records by FIELD (defauly '%default')", - type='string', metavar='FIELD', default='db_id') - parser.add_option('--pdf-title', dest='pdf_title', - help='Override the default PDF title', - type='string', metavar='TITLE') - parser.add_option('--inventory', dest='inventory', - help='Output a PDF inventory of matching records', - action='store_true', default=False) - parser.add_option('--door-warning', dest='door_warning', - help='Output a PDF door warning of matching records', - action='store_true', default=False) - parser.add_option('-t', '--test', dest='test', - help='Run docutils tests on db.py', - action='store_true', default=False) - parser.add_option('--list-locations', dest='locations', - help='List all currently used locations (no other output)', - action='store_true', default=False) - parser.add_option('-V', '--validate', dest='validate', - help='Validate CAS#s (no other output)', - action='store_true', default=False) - parser.add_option('-A', '--audit', dest='audit', - help='Search for troublesome entries (no other output)', - action='store_true', default=False) - parser.add_option('-v', '--verbose', dest='verbose', - help='Print lots of debugging information', - action='store_true', default=False) - - (options, args) = parser.parse_args() - parser.destroy() - - ifile,ofile = open_IOfiles(options.ifilename, options.ofilename, - options.verbose) - - if options.test : - _test() - elif options.locations : - db = text_db(filename=None) - pp = db_pretty_printer(db) - - # read in and parse the file - db._parse(ifile.read()) - - locations = [] - for record in db.records(): - if len(record['Location']) > 0 and record['Location'] not in locations: - locations.append(record['Location']) - locations.sort() - print >> ofile, '\n'.join(locations) - elif options.validate : - db = text_db(filename=None) - pp = db_pretty_printer(db) - - # read in and parse the file - db._parse(ifile.read()) - - CAS_DELIM = ',' # seperate CAS entries for chemicals with multiple CAS numbers - PERCENT_DELIM = ':' # seperate CAS number from ingredient percentage - for record in db.records() : - valid = True - cas = record['CAS#'] - if len(cas.split(CAS_DELIM)) == 0 : # cas = 'N...N-NN-N' - if not valid_CASno(cas, options.verbose) : - valid = False - print >> ofile, "Invalid CAS# in record: '%s'" % cas - else : # cas = 'N...N-NN-N:X%,N...N-NN-N:Y%,...' - for casterm in cas.split(CAS_DELIM) : # casterm = 'N...N-NN-N:X%' - c = casterm.split(PERCENT_DELIM)[0] # c = 'N...N-NN-N' - if not valid_CASno(c, options.verbose) : - valid = False - print >> ofile, "Invalid CAS* in record: '%s'" % c - if not valid : - print >> ofile, "in record %s: %s" % (record['ID'], record['Name']) - #pp.full_record_string(record) - elif options.audit : - db = text_db(filename=None) - pp = db_pretty_printer(db) - - # read in and parse the file - db._parse(ifile.read()) - - for record in db.records(): - # check for extra spaces - for key,value in record.items(): - if type(value) in types.StringTypes and value.strip() != value: - print >> ofile, "Extra whitespace for %s - %s field %s : '%s'" % (record['ID'], record['Name'], key, value) - # make sure we know the location of all current chemicals - if len(record['Disposed']) == 0 and len(record['Location']) == 0: - print >> ofile, "Misplaced record: %s - %s" % (record['ID'], record['Name']) - elif options.inventory: - db = text_db(filename=None) - pp = db_pretty_printer(db) - - # read in and parse the file - db._parse(ifile.read()) - - dgen = docgen(db) - def valid_record(r) : - return eval(options.valid_record, # expression - {'__builtins__':None}, # globals - {'r':r}) # locals - path = dgen.inventory(title=options.pdf_title, - namewidth=40, - sort_field=options.sort_field, - valid_record=valid_record) - print >> ofile, '\n', path - elif options.door_warning: - db = text_db(filename=None) - pp = db_pretty_printer(db) - - # read in and parse the file - db._parse(ifile.read()) - - dgen = docgen(db) - def valid_record(r) : - return eval(options.valid_record, # expression - {'__builtins__':None}, # globals - {'r':r}) # locals - path = dgen.door_warning(valid_record=valid_record) - print >> ofile, '\n', path - else : - db = text_db(filename=None) - - # read in and parse the file - db._parse(ifile.read()) - pp = db_pretty_printer(db) - if options.long_format : - for id in pp._norm_record_ids(options.print_records) : - string = pp.full_record_string_id(id) - else : - # pythonize the width option - if options.width == None or options.width == 'a': - width = options.width - elif len(options.width.split(':')) == 1 : - width = int(options.width) - elif len(options.width.split(':')) > 1 : - width = {} - for kv in options.width.split(',') : - spl = kv.split(':') - assert len(spl) == 2, 'invalid width "%s" in "%s"' % (kv, options.width) - if spl[1] == 'a' : - width[spl[0]] = spl[1] - else : - width[spl[0]] = int(spl[1]) - - string = pp.multi_record_string(options.print_records, - options.print_fields, - width, - options.FS) - print >> ofile, string, - - close_IOfiles(options.ifilename, ifile, - options.ofilename, ofile, options.verbose) diff --git a/chem_web.py b/chem_web.py deleted file mode 100755 index 85b316f..0000000 --- a/chem_web.py +++ /dev/null @@ -1,587 +0,0 @@ -#!/usr/bin/python -# -# Web application for posting additions/modifications to the chem-inventory -# derived from simplewiki and wiki_py, by Adam Bachman -# ( http://bachman.infogami.com/ ) -# Authentication following Snakelets -# http://snakelets.sourceforge.net/manual/authorization.html - -# Remember to delete the templates directory after making alterations, -# because this program only generates templates if they are missing. - - -## Bring in some useful goodies: -# web, because we're running a web server, and generating html; -# time, for timestamping backups; -# os, for creating the template directories; and -# re, for replacing internal node links with proper markup -import web, os, re -# md5, for hashing passwords -#import md5 - -# database must support the following methods : -# field_list() : return an ordered list of available fields (fields unique) -# long_field() : return an dict of long field names (keyed by field names) -# record(id) : return a record dict (keyed by field names) -# records() : return an ordered list of available records. -# backup() : save a copy of the current database somehow. -# set_record(i, newvals) : set a record by overwriting any preexisting data -# : with data from the field-name-keyed dict NEWVALS -import text_db -database = text_db.text_db -from chem_db import valid_CASno, MSDS_manager, docgen -DB_FILE = 'inventory.db' -import sys, daemon, logging -PID_FILE = './chem_web.pid' -LOG_FILE = './chem_web.log' - -## Also import a markup language, and associated regexp functions -from markdown import markdown -## for converting the first character in record names, and stripping | -from string import upper, rstrip - -## for SSL -SSL = False -if SSL : - from mk_simple_certs import get_cert_filenames - server_name = 'chem_web' - -__version__ = "0.3" - -## For web.py, when a URL matches '/view', handle with class 'view' -# when it matches '/edit', handle with class 'edit', -# and when it matches '/login', handle with class 'login', -# Note, there are no .html extension. -# -# link to edit pages using db_id -# link to MSDSs with ID -urls = ('/(view)?', 'view', - '/edit/([0-9]+)', 'edit', - '/MSDS/([0-9]+)', 'MSDS', - '/docs/([a-z._]*)', 'docs', - '/login', 'login') - -# limit the display width of selected fields -WIDTH_MAX = {'CAS#':12} - -# set the display width of entry fields -ENTRY_WIDTH = 50 - -class view (object) : - "Print the database" - # when the server recieves the command "GET '/view', call view.get('view') - def GET(self, name): - """ - Render the view.html template using name and the previous text. - If the file doesn't exist, use default text '%s doesn't exist'. - """ - if name == None : - name = 'view' - db._refresh() - recs = [] - for record in db.records() : - id = int(record['ID']) - record['ID'] = '%s' \ - % (id, record['ID']) - if MSDSman.has_MSDS(id) : # link the id to the MSDS - record['Name'] = '%s' \ - % (record['db_id'], record['Name']) - recs.append(record) - print render.view('Chemical inventory', - db.len_records(), db.field_list(), recs) - -class edit (object) : - "Provide methods for handling requests related to edit pages" - def GET(self, name): - """ - Render the edit.html template using the specified record number. - """ - db._refresh() - db_id = int(name) - if db_id >= db.len_records() : - logging.info("new record") - assert db_id == db.len_records(), \ - 'invalid id: %d (max %d)' % (db_id, db.len_records()) - record = db.new_record() - record['ID'] = str(record['db_id']) - db.set_record(db_id, record) - if MSDSman.has_MSDS(db_id) : - MSDSs = None - else : - # only ask for an MSDS if we still need one - MSDSs = MSDSman.get_all(simlinks=False) - print render.edit(int(name), db.field_list(), - db.long_fields(), db.record(int(name)), MSDSs) - def POST(self, name): - """ - Read the form input and update the database accordingly. - Then redirect to /view. - """ - db._refresh() - record = db.record(int(name)) - ## Generate a new record from the form input - # 'MSDS={}' to storify MSDS as a FieldStorage (dict-like) instance, - # otherwise it's saved as a string, and we loose info about it. - # e.g. newvals['MSDS'].type = 'text/html' - # The contents of the file are saved to newvals['MSDS'].value - newvals = web.input(MSDS={}) - update = False - for field in db.field_list() : - if newvals[field] != record[field] : - # TODO: add validation! - update=True - record[field] = newvals[field] - if 'MSDS source' in newvals : - # Handle any MSDS file actions - if newvals['MSDS source'] == 'upload' : - if len(newvals['MSDS'].filename) > 0 and len(newvals['MSDS'].value) > 0: - # only save if there is a file there to save ;) - #print >> stderr, web.ctx.env['CONTENT_TYPE'] - #print >> stderr, web.ctx.keys() - #print >> stderr, dir(newvals['MSDS']) - #print >> stderr, type(newvals['MSDS']) - #print >> stderr, newvals['MSDS'].filename - #print >> stderr, newvals['MSDS'].type - MSDSman.save(int(name), newvals['MSDS'].value, - newvals['MSDS'].type) - else : - logging.info('linking MSDS %d to %d' \ - % (int(record['ID']), - int(newvals['MSDS share'])) ) - MSDSman.link(int(record['ID']), - int(newvals['MSDS share'])) - if update : - db.set_record(int(name), record, backup=True) - # redirect to view all - web.seeother('/view') - -class MSDS (object) : - "Serve MSDS files by ID" - def GET(self, name): - "Serve MSDS files by ID" - id = int(name) - if MSDSman.has_MSDS(id) : - mime = MSDSman.get_MSDS_MIME(id) - web.header("Content-Type", mime) - print file(MSDSman.get_MSDS_path(id), 'rb').read() , - else : - print render.error(id) - -class docs (object) : - "Generate and serve assorted official documents" - def GET(self, name): - """ - List the available documents. - """ - db._refresh() - if name == '' : - print render.docs() - if name == 'inventory.pdf' : - path = dgen.inventory(namewidth=40) - print file(path, 'rb').read() , - if name == 'door_warning.pdf' : - path = dgen.door_warning() - print file(path, 'rb').read() , - def POST(self, name): - """ - Read the form input and print the appropriate file. - """ - db._refresh() - formdata = web.input() - user_regexp = formdata['regexp'] - regexp = re.compile(user_regexp, re.I) # Case insensitive - path = dgen.door_warning(lambda r: regexp.match(r['Location'])) - print file(path, 'rb').read() , - -class login (object) : - "Print an alphabetized index of all existing pages" - def GET(self): - print "Not yet implemented" - #print render.stat('login') - -class markup (object) : - "Convert text to html, using Markdown with a bit of preformatting" - def __init__(self) : - # [[optional display text|name with or_without_spaces]] - linkregexp = ('\[\[' - +'([^\|\[\]]*\|)?' - +'([a-zA-Z0-9-_ ]*)' - +'\]\]') - #print linkregexp - self.linkexp = re.compile(linkregexp) - self.linebreak = ' \n' - self.uscore = re.compile('_') - self.space = re.compile(' ') - def htmlize(self, text) : - return text - pre_markup = self._preformat(text) - #print "Preformatted '"+pre_markup+"'" - return self._markup( pre_markup ) - def _markup(self, text) : - # markdown() implements the text->html Markdown semantics - # the str() builtin ensures a nice, printable string - return str(markdown(text)) - def _preformat(self, text) : - #print "Preformatting '"+text+"'" - return self._autolink(text) - def _autolink(self, text) : - "Replace linkexps in text with Markdown syntax versions" - # sub passes a match object to link2markup for each match - # see http://docs.python.org/lib/match-objects.html - return self.linkexp.sub(self.matchlink2markup, text) - def matchlink2markup(self, match) : - # The name is the first (and only) matched region - #print match.groups() - name = match.groups()[1] - text = match.groups()[0] - return self.link2markup(text, name) - def linklist(self, text) : - linklist = [] # empty list - for m in self.linkexp.finditer(text) : - linklist.append( self.str2name(m.groups()[1]) ) - #print linklist - return linklist - def link2markup(self, text, name) : - """ - usage: string = link2markup(text, target) - takes the string name of a wiki page, - and returns a string that will be markuped into a link to that page - displaying the text text. - """ - # convert to Markdown pretty link syntax - if text : # remove trailing | - text = text.rstrip('|') - else : - text = self.name2str(name) - name = self.str2name(name) - return str('['+text+'](/'+name+')') - def name2str(self, name) : - """ - usage: string = name2str(name) - takes the string name of a wiki page, - and converts it to display format - See str2name() - """ - w_spaces = self.uscore.sub(' ', name) - return w_spaces - def str2name(self, string) : - """ - usage: string = name2str(name) - Converts strings to the relevent wiki page name. - See str2name() - """ - wo_spaces = self.space.sub('_', string) - cap_first = upper(wo_spaces[0]) + wo_spaces[1:] - return cap_first - def make_add_button(self, next_db_id) : - string = '
\n' % next_db_id - string += ' \n' - string += '

\n' - return string - def make_table(self, fields, records, width_max=WIDTH_MAX, - raw_fields=()): - """ - >>> print make_table(['A','B','C'],[{'A':'a','B':'b'},{'A':'d','B':'e','C':'f'}]), - - - - -
ABC
ab
def
- """ - # open the table - string = '\n' - # add the header - string += '' - for field in fields : - string += '' % self.htmlize(field) - string += '\n' - # add the records - for record in records : - string += '' - for field in fields : - rstring = record[field] - # truncate if the width is regulated... - if field in width_max : - w = width_max[field] - # ... and the full string is too long - if len(rstring) > w : - rstring = "%s..." % rstring[:w] - # if the field isn't raw, protect special chars - if not field in raw_fields : - rstring = self.htmlize(rstring) - string += '' % rstring - string += '\n' - # close the table - string += '
%s
%s
\n' - return string - def record_form_entries(self, index, fields, lfields, record, MSDSs=None, entry_width=ENTRY_WIDTH): - """ - >>> print record_form_entries(4,['A','B','MSDS'],{'A':'AA','B':'BB','MSDS'},{'A':'a','B':'b'}), - - - - - - - -
:
:
:
- """ - # open the table - string = '\n' - # add the record fields - for field in fields : - # get the record string - rstring = self.htmlize(record[field]) - fstring = self.htmlize(field) - lfstring = self.htmlize(lfields[field]) - string += ' \n' % (fstring, lfstring) - string += ' \n' \ - % (entry_width, fstring, fstring, rstring) - if MSDSs != None : - ## add an MSDS radio, share menu, and file upload fields - # radio - lfstring = fstring = 'MSDS source' - string += ' \n' \ - % (fstring, lfstring) - string += ' \n' \ - % (fstring, fstring) - - # file upload - fstring = 'MSDS' - lfstring = 'Upload MSDS' - string += ' \n' \ - % (fstring, lfstring) - string += ' \n' \ - % (entry_width, fstring, fstring) - - # file share menu - fstring = 'MSDS share' - lfstring = 'Use an already uploaded MSDS' - string += ' \n' \ - % (fstring, lfstring) - string += ' \n' - # close the table - string += '
:
:Upload\n' \ - % (fstring, fstring) - string += ' Share
:
:

\n' - return string - -class templt (object) : - "Handle some template wrapping" - def __init__(self) : - self.dir = 'templates/' - if not os.path.exists(self.dir): os.mkdir(self.dir) - ## Write simple template html pages if they don't already exist. - # see ( http://webpy.org/templetor ) for the syntax. - html=('\n' - '\n') - if not os.path.exists(self.dir+'view.html') : - view=('$def with (name, next_db_id, fields, records)\n' - +html+ - ' \n' - ' \n' - ' $:name2str(name) \n' - ' \n' - ' \n' - ' \n' - '

\n' - ' $:name2str(name)\n' - '

\n' - ' See \n' - ' the rules\n' - ' for more information.\n' - ' See the docs page to generate required documents.
\n' - '
\n' - ' $:make_add_button(next_db_id)\n' - ' $:make_table(fields, records)\n' - ' $:make_add_button(next_db_id)\n' - ' \n' - '\n') - file(self.dir+'view.html', 'w').write(view) - if not os.path.exists(self.dir+'edit.html') : - # note: - # the form encoding type 'enctype="multipart/form-data">\n' - # is only required because of the MSDS file-upload field. - edit=('$def with (index, fields, lfields, record, MSDSs)\n' - +html+ - ' \n' - ' \n' - ' $:htmlize(record["Name"]) \n' - ' \n' - ' \n' - ' \n' - '

\n' - ' Editing: $:htmlize(record["Name"]) \n' - '

\n' - '
\n' - ' $:record_form(index, fields, lfields, record, MSDSs)
\n' - ' \n' - '
\n' - ' \n' - '\n') - file(self.dir+'edit.html', 'w').write(edit) - if not os.path.exists(self.dir+'error.html') : - # like view, but no edit ability - # since the content is generated, - # or backlink list, since there would be so many. - stat=('$def with (id)\n' - +html+ - ' \n' - ' \n' - ' \n' - '

Error

\n' - ' There is currently no MSDS file for \n' - ' $:htmlize(id)\n' - ' \n' - '\n') - file(self.dir+'error.html', 'w').write(stat) - if not os.path.exists(self.dir+'docs.html') : - docs=(html + - ' \n' - ' \n' - ' \n' - '

\n' - ' Inventory\n' - ' in accordance with the \n' - ' \n' - ' Chemical Hygiene Plan Section E-7.
\n' - ' Door warning\n' - ' in accordance with the Chemical Hygiene Plan Sections\n' - ' E-7\n' - ' and \n' - ' E-10\n' - ' .
\n' - '

\n' - '

\n' - ' For door warnings for subsections of the whole room,\n' - ' please give a location regexp in the form below.\n' - ' For example: ".*liquids" or "refrigerator".\n' - '

\n' - '
\n' - ' \n' - ' \n' - ' \n' - '
Location regexp:
\n' - ' \n' - '
\n' - ' \n' - '\n') - file(self.dir+'docs.html', 'w').write(docs) - - -class chem_web_daemon (daemon.Daemon) : - gid = None - uid = None - pidfile = PID_FILE - logfile = LOG_FILE - loglevel = 'INFO' - def run(self) : - if self.pkey_file == None or self.cert_file == None : - logging.info("http://%s:%d/" % web.validip(self.options.ip)) - else : - logging.info("https://%s:%d/" % web.validip(self.options.ip)) - - ## web.py should give detailed error messages, not just `internal error' - web.internalerror = web.debugerror - - ## How we'd start webpy server if we didn't need command line args or SSL - # Pass web my URL regexps, and the globals from this script - # You can also pass it web.profiler to help optimize for speed - #web.run(urls, globals()) - ## How we have to start it now - webpy_func = web.webpyfunc(urls, globals(), False) - wsgi_func = web.wsgifunc(webpy_func) - web.httpserver.runsimple(wsgi_func, - web.validip(self.options.ip), - ssl_private_key_filename=self.pkey_file, - ssl_certificate_filename=self.cert_file) - - def read_basic_config(self) : - pass - def parse_options(self): - from optparse import OptionParser - - usage_string = ('%prog [options]\n' - '\n' - '2008, W. Trevor King.\n') - version_string = '%%prog %s' % __version__ - parser = OptionParser(usage=usage_string, version=version_string) - - # Daemon options - parser.add_option('--start', dest='action', - action='store_const', const='start', default='start', - help='Start the daemon (the default action)') - parser.add_option('--stop', dest='action', - action='store_const', const='stop', default='start', - help='Stop the daemon') - parser.add_option('-n', '--nodaemon', dest='daemonize', - action='store_false', default=True, - help='Run in the foreground') - - # Server options - parser.add_option('-a', '--ip-address', dest="ip", - help="IP address (default '%default')", - type='string', metavar="IP", default='0.0.0.0:8080') - parser.add_option('-s', '--secure', dest="secure", - help="Run in secure (HTTPS) mode.", - type='string', metavar="PKEY_FILE:CERT_FILE") - parser.add_option('-v', '--verbose', dest="verbose", action="store_true", - help="Print lots of debugging information", - default=False) - - self.options, self.args = parser.parse_args() - parser.destroy() - - if self.options.verbose : - self.loglevel = 'DEBUG' - # get options for httpserver - if self.options.secure != None : - split = self.options.secure.split(':') - assert len(split) == 2, "Invalid secure argument '%s'" - self.pkey_file = split[0] - self.cert_file = split[1] - else : - self.pkey_file = None - self.cert_file = None - -### the following instances and definitions must have -## global scope. because they are called from inside web -# create the database -db = database(filename=DB_FILE) -MSDSman = MSDS_manager(db) -dgen = docgen(db) - -## set up the templates -tmplt = templt() -# Tell templator where to look for templates -# to provide a framework for the generated webpages -render = web.template.render(tmplt.dir) - -## Define markup functions -mkup = markup() -htmlize = lambda t : mkup.htmlize(t) -name2str = lambda n : mkup.name2str(n) -mktable = lambda h,r : mkup.make_table(h,r,WIDTH_MAX,raw_fields=('ID','Name')) -mkadd = lambda ni : mkup.make_add_button(ni) -record_form = lambda i,f,l,r,M : mkup.record_form_entries(i,f,l,r,M) -## Give templates access to the htmlize, make_table, and name2str functions -# ( see http://webpy.org/templetor and our view.html ) -web.template.Template.globals['htmlize'] = htmlize -web.template.Template.globals['make_table'] = mktable -web.template.Template.globals['make_add_button'] = mkadd -web.template.Template.globals['name2str'] = name2str -web.template.Template.globals['record_form'] = record_form - - -## If this script is run from the command line, -# use the tools we've just defined to host the chemical inventory -if __name__=="__main__": - chem_web_daemon().main() diff --git a/chemdb/__init__.py b/chemdb/__init__.py new file mode 100644 index 0000000..b98f164 --- /dev/null +++ b/chemdb/__init__.py @@ -0,0 +1 @@ +# Copyright diff --git a/chemdb/chemdb.py b/chemdb/chemdb.py new file mode 100644 index 0000000..c9102c0 --- /dev/null +++ b/chemdb/chemdb.py @@ -0,0 +1,379 @@ +# Copyright + +"""Utilities for chemical inventories. + +Includes a CAS number validator and document generation. +""" + +import re +import os +import os.path +import time +import types +from sys import stdin, stdout, stderr + +from .db.text import DBPrettyPrinter + + +def valid_CASno(cas_string, debug=False): + """Validate CAS numbers. + + Check `N..NN-NN-N` format, and the `checksum digit`_ for valid CAS + number structure. for + + .. math:: + N_n .. N_4 N_3 - N_2 N_1 - R + + The checksum digit is + + .. math:: + R = remainder([sum_{i=1}^n i N_i ] / 10 ) + + .. _checksum digit: + http://www.cas.org/expertise/cascontent/registry/checkdig.html + + >>> valid_CASno('107-07-3') + True + >>> valid_CASno('107-08-3') + False + >>> valid_CASno('107-083') + False + + Sometimes we don't have a CAS number, or a product will contain + secret, non-hazardous ingredients. Therefore we treat the strings + `na` and `+secret-non-hazardous` as valid CAS numbers. + + >>> valid_CASno('na') + True + >>> valid_CASno('+secret-non-hazardous') + True + """ + if cas_string in ['na', '+secret-non-hazardous']: + return True + # check format, + # \A matches the start of the string + # \Z matches the end of the string + regexp = re.compile('\A[0-9]{2,}[-][0-9]{2}[-][0-9]\Z') + if regexp.match(cas_string) == None: + if debug: print >> stderr, "invalid CAS# format: '%s'" % cas_string + return False + # generate check digit + casdigs = [int(d) for d in ''.join(cas_string.split('-'))] + sumdigs = casdigs[:-1] + sumdigs.reverse() + s = sum([(i+1)*d for i,d in enumerate(sumdigs)]) + check = s % 10 + if check == casdigs[-1]: + return True + elif debug: + print >> stderr, ( + "invalid CAS# check: '%s' (expected %d)" % (cas_string, check)) + return False + +class MSDSManager (object): + """Manage Material Saftey Data Sheets (MSDSs). + """ + def __init__(self, db, dir="./MSDS/"): + self.db = db + self.dir = dir + self.MIMEs = { + 'application/pdf': ['pdf'], + 'text/html': ['html'], + 'text/plain': ['txt'], + } + self.check_dir() + + def check_dir(self): + "Create the MSDS directory if it's missing." + if os.path.isdir(self.dir): + return # all set to go + elif os.path.exists(self.dir): + raise Exception, ( + 'Error: a non-directory file exists at %s' % self.dir) + else: + os.mkdir(self.dir) + + def basepath(self, id): + assert isinstance(id, int), ( + 'id must be an integer, not %s (%s)' % (type(id), str(id))) + return os.path.join(self.dir, "%d" % id) + + def local_basepath(self, id) : # for symbolic links + assert isinstance(id, int), ( + 'id must be an integer, not %s (%s)' % (type(id), str(id))) + return "./%d" % id + + def MIME_ext(self, mime): + if mime in self.MIMEs.keys(): + return self.MIMEs[mime][0] + for values in self.MIMEs.values(): + if mime in values: + return mime + raise ValueError( + "invalid MIME type '%s'\nshould be one of %s" % (mime, self.MIMEs)) + + def path(self, id, mime): + return "%s.%s" % (self.basepath(id), self.MIME_ext(mime)) + + def local_path(self, id, mime): + return "%s.%s" % (self.local_basepath(id), self.MIME_ext(mime)) + + def save(self, id, filetext, mime='application/pdf'): + "Save the binary byte string FILE to the path for ID" + print >> file(self.path(id, mime), 'wb'), filetext, + + def link(self, id, target_id): + # target_id already exists, create a symlink to it for id. + target_mime = self.get_MSDS_MIME(target_id) + target_path = self.local_path(target_id, target_mime) + path = self.path(id, target_mime) + #os.link(self.path(target_id), self.path(id)) # hard link... + os.symlink(target_path, path) # ... or soft link + + def has_MSDS_MIME(self, id, mime): + """ + >>> m = MSDSManager(db=None) + >>> print m.has_MSDS_MIME(102, 'pdf') # test on html + False + >>> print m.has_MSDS_MIME(102, 'html') # test on html + True + >>> print m.has_MSDS_MIME(6, 'pdf') # test on pdf symlink + True + """ + return os.path.exists(self.path(id, mime)) + + def get_MSDS_path(self, id): + """ + >>> m = MSDSManager(db=None) + >>> print m.get_MSDS_path(102) # test on html + ./MSDS/102.html + >>> print m.get_MSDS_path(1) # test on pdf + ./MSDS/1.pdf + >>> print m.get_MSDS_path(6) # test on pdf symlink + ./MSDS/6.pdf + """ + for mime in self.MIMEs: + if self.has_MSDS_MIME(id, mime): + return self.path(id, mime) + return None + + def get_MSDS_MIME(self, id): + """ + >>> m = MSDSManager(db=None) + >>> print m.get_MSDS_MIME(102) # test on html + text/html + >>> print m.get_MSDS_MIME(1) # test on pdf + application/pdf + >>> print m.get_MSDS_MIME(6) # test on pdf symlink + application/pdf + """ + for mime in self.MIMEs: + if self.has_MSDS_MIME(id, mime): + return mime + return None + + def has_MSDS(self, id): + if self.get_MSDS_path(id) == None: + return False + return True + + def get_all(self, simlinks=True): + ret = [] + for record in self.db.records(): + p = self.get_MSDS_path( int(record['ID']) ) + if p != None: + if simlinks == False and os.path.islink( p ): + continue # ignore the symbolic link + ret.append({'ID':record['ID'], 'Name':record['Name']}) + return ret + + +class DocGen (object): + "Generate the officially required documents" + def __init__(self, db, doc_root=os.path.join('template', 'doc')): + self.db = db + self.doc_root = doc_root + + def _latex_safe(self, string): + string = string.replace('%', '\%') + string = string.replace('>', '$>$') + string = string.replace('<', '$<$') + return string + + def _set_main_target(self, target): + print >> file(os.path.join(self.doc_root, 'main.tex'), 'w'), ( + """\documentclass[letterpaper]{article} + +\input{%s} +""" % target) + + def _make_pdf(self, target_file): + os.system('cd %s && make pdf' % self.doc_root) + path = os.path.join(self.doc_root, target_file) + os.system('cp %s %s' % (os.path.join(self.doc_root, 'main.pdf'), path)) + return path + + def inventory(self, title=None, + namewidth='a', sort_field='db_id', + valid_record=lambda r: r['Disposed'] == ''): + """Create a pdf list of all maching chemicals. The default is to + match all currently owned chemicals. Matching chemicals can be sorted + by any field (defaults to 'ID').""" + if title == None: + title == 'Inventory' + pp = DBPrettyPrinter(self.db) + active_ids = [] + for record in self.db.records(): + if valid_record(record) : # get ids for matching chemicals + active_ids.append(record['db_id']) + active_ids.sort(cmp=lambda a,b: cmp(self.db.record(a)[sort_field], + self.db.record(b)[sort_field])) + active_fields = ['ID', 'Name', 'Amount', + 'H', 'F', 'R', 'O', 'M', 'C', 'T'] + width = {} + for field in active_fields: + width[field] = 'a' + width['Name'] = namewidth + ## Plain text method + #string = "Chemical inventory:\t\tGenerated on %s\n\n" \ + # % time.strftime('%Y-%m-%d') + #string += pp.multi_record_string(active_ids, active_fields, + # width=width, FS=' ') + # return string + ## Latex method + string = "\\begin{longtable}{l l l c c c c c c c}\n" + string += ('%% The header for the remaining page(s) of the table...\n' + 'ID & Name & Amount & H & F & R & O & M & C & T \\\\\n' + '\\hline\n' + '\\endhead\n') + for db_id in active_ids: + record = self.db.record(db_id) + string += " %s & %s & %s & %s & %s & %s & %s & %s & %s & %s \\\\\n" \ + % (self._latex_safe(record['ID']), + self._latex_safe(record['Name']), + self._latex_safe(record['Amount']), + self._latex_safe(record['H']), + self._latex_safe(record['F']), + self._latex_safe(record['R']), + self._latex_safe(record['O']), + self._latex_safe(record['M']), + self._latex_safe(record['C']), + self._latex_safe(record['T'])) + string += "\\end{longtable}\n" + print >> file(os.path.join(self.doc_root, 'inventory_title.tex'), 'w'), title + print >> file(os.path.join(self.doc_root, 'inventory_data.tex'), 'w'), string + ## alter main.tex to point to the inventory template. + self._set_main_target('inventory_template') + ## run latex + path = self._make_pdf('inventory.pdf') + return path + + def door_warning(self, + valid_record=lambda r: r['Disposed'] == ''): + """create a warning NFPA diamond and list of the most dangerous + chemicals for which valid_record(record) is true. For + example, to generate a door warning for the front door use + door_warning(lambda r: r['Disposed'] == '') + or to generate the warning for the fridge + door_warning(lambda r: r['Location'] == 'Refrigerator') + Note that valid_record defaults to the first example. + """ + pp = DBPrettyPrinter(self.db) + all_ids = range(self.db.len_records()) + + # Search the database to find the nasties + NFPA_maxs = {'H':0, 'F':0, 'R':0, 'O':[]} + Mutagens = [] + Carcinogens = [] + Teratogens = [] + Healths = [] + Fires = [] + Reactivities = [] + Others = [] + for record in self.db.records(): + if valid_record(record): + for field in ['H', 'F', 'R', 'O']: + r = record[field] + if r != '' and r != '?': + if field != 'O' and int(r) > NFPA_maxs[field]: + NFPA_maxs[field] = int(r) + elif field == 'O' and not r in NFPA_maxs['O']: + NFPA_maxs[field].append(r) + for field,array in zip(['M','C','T'], + [Mutagens, + Carcinogens, + Teratogens]): + if record[field] != '' and record[field] != '?': + array.append(record['db_id']) + # now that we've found the max NFPAs, + # find all the chemicals at those levels + for record in self.db.records(): + if valid_record(record): + for field,array in zip(['H', 'F', 'R', 'O'], + [Healths, Fires, + Reactivities, Others]): + r = record[field] + if r != '' and r != '?': + if field != 'O' and int(r) == NFPA_maxs[field]: + array.append(record['db_id']) + elif field == 'O' and r in NFPA_maxs['O']: + array.append(record['db_id']) + + ## generate the output + # first, update the NFPA grapic code + if 'OX' in NFPA_maxs['O'] : OX = 'y' + else : OX = 'n' + if 'W' in NFPA_maxs['O'] : W = 'y' + else : W = 'n' + os.system('%s %d %d %d %s %s > %s' + % (os.path.join(self.doc_root, 'gen_NFPA.sh'), + NFPA_maxs['H'], NFPA_maxs['F'], NFPA_maxs['R'], OX, W, + os.path.join(self.doc_root, 'mp', 'NFPA.mp'))) + # now generate a list of the nasties ( Amount & ID & Name ) + string = "\\begin{tabular}{r r l}\n" + for field,name,array in zip(['H', 'F', 'R', 'O'], + ['Health', 'Fire', + 'Reactivity', 'Other'], + [Healths, Fires, + Reactivities, Others]): + if (not hasattr(NFPA_maxs[field], '__len__')) \ + or len(NFPA_maxs[field]) > 0: + string += " \multicolumn{3}{c}{\Tstrut %s : %s} \\\\\n" \ + % (name, NFPA_maxs[field]) + else : # Print "Other" instead of "Other : []" + string += " \multicolumn{3}{c}{\Tstrut %s} \\\\\n" \ + % (name) + for db_id in array: + record = self.db.record(db_id) + string += " %s & %s & %s \\\\\n" \ + % (self._latex_safe(record['Amount']), + self._latex_safe(record['ID']), + self._latex_safe(record['Name'])) + if len(array) == 0: + string += " \multicolumn{3}{c}{ --- } \\\\\n" + for hazard,array in zip(['Mutagens','Carcinogens','Teratogens'], + [Mutagens, Carcinogens, Teratogens]): + string += " \multicolumn{3}{c}{\Tstrut %s} \\\\\n" % (hazard) + for db_id in array: + record = self.db.record(db_id) + string += " %s & %s & %s \\\\\n" \ + % (self._latex_safe(record['Amount']), + self._latex_safe(record['ID']), + self._latex_safe(record['Name'])) + if len(array) == 0: + string += " \multicolumn{3}{c}{ --- } \\\\\n" + string += "\\end{tabular}\n" + print >> file(os.path.join(self.doc_root, 'door_data.tex'), 'w'), string + ## alter main.tex to point to the door template. + self._set_main_target('door_template') + ## run latex + path = self._make_pdf('door_warning.pdf') + return path + + +def _test(): + import doctest + doctest.testmod() + +if __name__ == "__main__": + _test() diff --git a/daemon.py b/chemdb/daemon.py similarity index 100% rename from daemon.py rename to chemdb/daemon.py diff --git a/chemdb/db/__init__.py b/chemdb/db/__init__.py new file mode 100644 index 0000000..b98f164 --- /dev/null +++ b/chemdb/db/__init__.py @@ -0,0 +1 @@ +# Copyright diff --git a/text_db.py b/chemdb/db/text.py similarity index 58% rename from text_db.py rename to chemdb/db/text.py index eca4740..8d731a1 100644 --- a/text_db.py +++ b/chemdb/db/text.py @@ -1,27 +1,46 @@ -#!/usr/bin/python -""" -Simple database-style interface to text-delimited, single files. -Use this if, for example, your coworkers insist on keeping data compatible with M$ Excel. +# Copyright + +"""Database-style interface with a text-delimited, single files. + +Use this if, for example, your coworkers insist on keeping data +compatible with M$ Excel. """ import copy +import os +import os.path +import shutil +import stat from sys import stdin, stdout, stderr +import time +import types -# import os, shutil, and chem_db for managing the database files -import os, shutil, stat, time -import os.path FILE = 'default.db' STANDARD_TAB = 8 -class fieldError (Exception) : + +class IndexStringError (Exception): + "invalid index string format" + pass + + +class FieldError (Exception): "database fields are not unique" pass -class text_db (object) : - """ - Define a simple database interface for a spread-sheet style database file. - + +class MissingDatabaseFile (Exception): + "Specified database file does not exist" + def __init__(self, path): + msg = "Missing database file %s" % path + Exception.__init__(self, msg) + self.path = path + + +class TextDB (object): + """Simple database interface for a spread-sheet style database file. + field_list() : return an ordered list of available fields (fields unique) long_fields() : return an dict of long field names (keyed by field names) record(id) : return a record dict (keyed by field names) @@ -32,7 +51,7 @@ class text_db (object) : new_record() : add a blank record (use set_record to change its values) """ def __init__(self, filename=FILE, COM_CHAR='#', FS='\t', RS='\n', - current_dir='./current/', backup_dir='./backup/' ) : + current_dir='./current/', backup_dir='./backup/' ): self.filename = filename self.COM_CHAR = COM_CHAR # comment character (also signals header row) self.FS = FS # field seperator @@ -41,198 +60,210 @@ class text_db (object) : # define directories used by the database self.cur = current_dir self.bak = backup_dir - - if self.filename == None : + + if self.filename == None: return # for testing, don't touch the file system - + ## Generate the neccessary directory structure if neccessary - for d in [self.cur,self.bak] : + for d in [self.cur, self.bak]: self.check_dir(d) self._open() - + # directory and file IO operations - def check_dir(self, dir) : + + def check_dir(self, dir): "Create the database directory if it's missing" - if os.path.isdir(dir) : + if os.path.isdir(dir): return # all set to go - elif os.path.exists(dir) : + elif os.path.exists(dir): raise Exception, "Error: a non-directory file exists at %s" % dir - else : + else: os.mkdir(dir) - def curpath(self) : + + def curpath(self): "Return the path to the current database file." return os.path.join(self.cur, self.filename) - def _get_mtime(self) : + + def _get_mtime(self): "Get the timestamp of the last modification to the database." s = os.stat(self.curpath()) return s[stat.ST_MTIME] - def exists(self) : + + def exists(self): "Check if the database exists" - # for some reason, my system's os.path.exists - # returns false for valid symbolic links... return os.path.exists(self.curpath()) - def _assert_exists(self) : - """ - Assert that the database exists on disk. + + def _assert_exists(self): + """Assert that the database exists on disk. + Print a reasonable error if it does not. """ if not self.exists(): - raise missingDatabaseFile(self.curpath()) - def _open(self) : + raise MissingDatabaseFile(self.curpath()) + + def _open(self): "Load the database from disk" self._assert_exists() - # precedence AND > OR fulltext = file(self.curpath(), 'r').read() self._mtime = self._get_mtime() self._parse(fulltext) - def iscurrent(self) : + + def iscurrent(self): "Check if our memory-space db is still syncd with the disk-space db." return self._mtime == self._get_mtime() - def _refresh(self) : + + def _refresh(self): "If neccessary, reload the database from disk." - if not self.iscurrent() : + if not self.iscurrent(): self._open() - def _save(self) : + + def _save(self): "Create a new database file from a header and list of records." - # save the new text fid = file(self.curpath(), 'w') fid.write( self._file_header_string(self._header) ) - if self._long_header : + if self._long_header: fid.write( self._file_header_string(self._long_header) ) - for record in self._records : + for record in self._records: fid.write( self._file_record_string(record) ) fid.close() - def backup(self) : + + def backup(self): "Back up database file" if not self.exists(): return None # nothing to back up. # Append a timestamp to the file & copy to self.bak - # the str() builtin ensures a nice, printable string - tname = self.filename+'.'+str(int(time.time())) + tname = '%s.%d' % (self.filename, time.time()) tpath = os.path.join(self.bak, tname) spath = self.curpath() shutil.copy(spath, tpath) - + + # file-text to memory operations + def _get_header(self, head_line, assert_unique=False, - assert_no_db_id_field=True) : - """ - Parse a header line (starts with the comment character COM_CHAR). - + assert_no_db_id_field=True): + """Parse a header line (starts with the comment character COM_CHAR). + Because doctest doesn't play well with tabs, use colons as field seps. - >>> db = text_db(FS=':', filename=None) + >>> db = TextDB(FS=':', filename=None) + >>> print db._get_header("#Name:Field 1:ID: another field") ['Name', 'Field 1', 'ID', ' another field'] - >>> try : + >>> try: ... x = db._get_header("#Name:Field 1:Name: another field", assert_unique=True) - ... except fieldError, s : + ... except FieldError, s: ... print s fields 0 and 2 both 'Name' """ assert len(head_line) > 0, 'empty header' assert head_line[0] == self.COM_CHAR, 'bad header: "%s"' % head_line fields = head_line[1:].split(self.FS) - if assert_unique : - for i in range(len(fields)) : - for j in range(i+1,len(fields)) : - if fields[i] == fields[j] : - raise fieldError, "fields %d and %d both '%s'" \ + if assert_unique: + for i in range(len(fields)): + for j in range(i+1,len(fields)): + if fields[i] == fields[j]: + raise FieldError, "fields %d and %d both '%s'" \ % (i,j,fields[i]) - if assert_no_db_id_field : - for i in range(len(fields)) : - if fields[i] == self.db_id_field : - raise fieldError, "fields %d uses db_id field '%s'" \ + if assert_no_db_id_field: + for i in range(len(fields)): + if fields[i] == self.db_id_field: + raise FieldError, "fields %d uses db_id field '%s'" \ % (i,fields[i]) return fields - def _get_fields(self, line, num_fields=None) : - """ - Parse a record line. - + + def _get_fields(self, line, num_fields=None): + """Parse a record line. + Because doctest doesn't play well with tabs, use colons as field seps. - >>> db = text_db(FS=':', filename=None) + >>> db = TextDB(FS=':', filename=None) + >>> print db._get_fields("2-Propanol:4 L:67-63-0:Fisher:6/6/2004",7) ['2-Propanol', '4 L', '67-63-0', 'Fisher', '6/6/2004', '', ''] """ vals = line.split(self.FS) - if num_fields != None : + if num_fields != None: assert len(vals) <= num_fields, "Too many values in '%s'" % line - for i in range(len(vals), num_fields) : + for i in range(len(vals), num_fields): vals.append('') # pad with empty strings if neccessary return vals - def _parse(self, text) : + + def _parse(self, text): reclines = text.split(self.RS) assert len(reclines) > 0, "Empty database file" - self._header = self._get_header(reclines[0], assert_unique=True) + self._header = self._get_header(reclines.pop(0), assert_unique=True) self._long_header = None self._records = [] - if len(reclines) == 1 : + if len(reclines) == 0: return # Only a header # check for a long-header line - if len(reclines[1]) > 0 and reclines[1][0] == self.COM_CHAR : - self._long_header = self._get_header(reclines[1]) - startline = 2 - else : - startline = 1 - for recline in reclines[startline:] : - if len(recline) == 0 : - continue # ignore blank lines + if len(reclines[0]) > 0 and reclines[0].startswith(self.COM_CHAR): + self._long_header = self._get_header(reclines.pop(0)) + for recline in reclines: + if len(recline) == 0 or recline.startswith(self.COM_CHAR): + continue # ignore blank lines and comments self._records.append(self._get_fields(recline, len(self._header))) - - + # memory to file-text operations - def _file_record_string(self, record) : - """ - Format record for creating a new database file. - + + def _file_record_string(self, record): + """Format record for creating a new database file. + Because doctest doesn't play well with tabs, use colons as field seps. - >>> db = text_db(FS=':', RS=';', filename=None) - >>> rs="2-Propanol:4 L:67-63-0:BPA426P-4:Fisher:6/6/2004:2:3:0" - >>> print db._file_record_string( db._get_fields(rs)) == (rs+";") - True + >>> db = TextDB(FS=':', RS=';', filename=None) + + >>> rs = '2-Propanol:4 L:67-63-0:Fisher:6/6/2004:2:3:0' + >>> db._file_record_string(db._get_fields(rs)) + '2-Propanol:4 L:67-63-0:Fisher:6/6/2004:2:3:0;' """ return "%s%s" % (self.FS.join(record), self.RS) - def _file_header_string(self, header) : - """ - Format header for creating a new database file. - """ + + def _file_header_string(self, header): + "Format header for creating a new database file." return "%s%s%s" % (self.COM_CHAR, self.FS.join(header), self.RS) - - # nice, stable api for our users - def field_list(self) : - "return an ordered list of available fields (fields unique)" + + # nice, stable API for our users + + def field_list(self) : + "Return an ordered list of available fields (fields unique)" return copy.copy(self._header) - def long_fields(self) : - "return an dict of long field names (keyed by field names)" - if self._long_header : + + def long_fields(self): + "Return a dict of long field names (keyed by field names)" + if self._long_header: return dict(zip(self._header, self._long_header)) else : # default to the standard field names return dict(zip(self._header, self._header)) - def record(self, db_id) : - "return a record dict (keyed by field names)" - assert type(db_id) == type(1), "id %s not an int!" % str(db_id) - assert db_id < len(self._records), "record %d does not exist" % db_id + + def record(self, db_id): + "Return a record dict (keyed by field names)" + assert isinstance(db_id, int), "id %s not an int!" % str(db_id) + assert db_id >= 0 and db_id < len(self._records), ( + "record %d does not exist" % db_id) d = dict(zip(self._header, self._records[db_id])) d['db_id'] = db_id return d - def records(self) : - "return an ordered list of available records." + + def records(self): + "Return an ordered list of available records." ret = [] - for id in range(len(self._records)) : + for id in range(len(self._records)): ret.append(self.record(id)) return ret - def len_records(self) : - "return len(self.records()), but more efficiently" + + def len_records(self): + "Return len(self.records()), but more efficiently" return len(self._records) - def set_record(self, db_id, newvals, backup=True) : - """ - set a record by overwriting any preexisting data - with data from the field-name-keyed dict NEWVALS + + def set_record(self, db_id, newvals, backup=True): + """Set a record with data from the field-name-keyed dict `newvals`. + + Overwrites any preexisting data. """ - if backup : + if backup: self.backup() - for k,v in newvals.items() : - if k == self.db_id_field : + for k,v in newvals.items(): + if k == self.db_id_field: assert int(v) == db_id, \ "don't set the db_id field! (attempted %d -> %d)" \ % (db_id, int(v)) @@ -243,80 +274,71 @@ class text_db (object) : # overwrite the record value self._records[db_id][fi] = v self._save() - def new_record(self, db_id=None) : - """ - create a blank new record and return it. + + def new_record(self, db_id=None): + """Create a blank new record and return it. """ record = {} - for field in self._header : - record[field] = "" + for field in self._header: + record[field] = '' record[self.db_id_field] = len(self._records) self._records.append(['']*len(self._header)) return record -class missingDatabaseFile (Exception) : - "Specified database file does not exist" - def __init__(self, path): - msg = "Missing database file %s" % path - Exception.__init__(self, msg) - self.path = path - -class indexStringError (Exception) : - "invalid index string format" - pass - -class db_pretty_printer (object) : - """ - Define some pretty-print functions for text_db objects. +class DBPrettyPrinter (object): + """Define some pretty-print functions for :class:`TextDB` objects. """ - def __init__(self, db) : + def __init__(self, db): self.db = db - def _norm_active_fields(self, active_fields_in=None) : - """ - Normalize the active field parameter - - >>> db = text_db(FS=':', RS=' ; ', filename=None) - >>> pp = db_pretty_printer(db) + + def _norm_active_fields(self, active_fields_in=None): + """Normalize the active field parameter + + >>> from pprint import pprint + >>> db = TextDB(FS=':', RS=' ; ', filename=None) + >>> pp = DBPrettyPrinter(db) >>> db._parse("#Name:Amount:CAS#:Vendor ; 2-Propanol:4 L:67-63-0:Fisher") - >>> print pp._norm_active_fields(None) == {'Name':True, 'Amount':True, 'CAS#':True, 'Vendor':True} - True - >>> print pp._norm_active_fields(['Vendor', 'Amount']) == {'Name':False, 'Amount':True, 'CAS#':False, 'Vendor':True} - True - >>> print pp._norm_active_fields('1:3') == {'Name':False, 'Amount':True, 'CAS#':True, 'Vendor':False} - True + + >>> pprint(pp._norm_active_fields(None)) + {'Amount': True, 'CAS#': True, 'Name': True, 'Vendor': True} + >>> pprint(pp._norm_active_fields(['Vendor', 'Amount'])) + {'Amount': True, 'CAS#': False, 'Name': False, 'Vendor': True} + >>> pprint(pp._norm_active_fields('1:3')) + {'Amount': True, 'CAS#': True, 'Name': False, 'Vendor': False} """ - if active_fields_in == None : + if active_fields_in == None: active_fields = {} - for field in self.db.field_list() : + for field in self.db.field_list(): active_fields[field] = True return active_fields - elif type(active_fields_in) == type('') : + elif isinstance(active_fields_in, types.StringTypes): active_i = self._istr2ilist(active_fields_in) active_fields = {} fields = self.db.field_list() - for i in range(len(fields)) : - if i in active_i : + for i in range(len(fields)): + if i in active_i: active_fields[fields[i]] = True - else : + else: active_fields[fields[i]] = False - else : - if type(active_fields_in) == type([]) : + else: + if isinstance(active_fields_in, list): active_fields = {} - for field in active_fields_in : + for field in active_fields_in: active_fields[field] = True - elif type(active_fields_in) == type({}) : + elif isinstance(active_fields_in, dict): active_fields = active_fields_in - assert type(active_fields) == type({}), 'by this point, should be a dict' - for field in self.db.field_list() : - if not field in active_fields : + assert isinstance(active_fields, dict), 'by this point, should be a dict' + for field in self.db.field_list(): + if not field in active_fields: active_fields[field] = False return active_fields - def full_record_string(self, record, active_fields=None) : + + def full_record_string(self, record, active_fields=None): """ Because doctest doesn't play well with tabs, use colons as field seps. - >>> db = text_db(FS=':', RS=' ; ', filename=None) - >>> pp = db_pretty_printer(db) + >>> db = TextDB(FS=':', RS=' ; ', filename=None) + >>> pp = DBPrettyPrinter(db) >>> db._parse("#Name:Amount:CAS#:Vendor ; 2-Propanol:4 L:67-63-0:Fisher") >>> print pp.full_record_string( db.record(0) ), Name : 2-Propanol @@ -329,57 +351,59 @@ class db_pretty_printer (object) : active_fields = self._norm_active_fields(active_fields) # scan through and determine the width of the largest field w = 1 - for field in fields : - if active_fields[field] and len(field) > w : + for field in fields: + if active_fields[field] and len(field) > w: w = len(field) # generate the pretty-print string string = "" - for field in fields : - if field in active_fields and active_fields[field] : + for field in fields: + if field in active_fields and active_fields[field]: string += "%*.*s : %s\n" \ % (w, w, long_fields[field], record[field]) return string - def full_record_string_id(self, id, active_fields=None) : + + def full_record_string_id(self, id, active_fields=None): record = self.db.record(id) return self.full_record_string(record, active_fields) - def _istr2ilist(self, index_string) : - """ - Generate index lists from assorted string formats. - + + def _istr2ilist(self, index_string): + """Generate index lists from assorted string formats. + Parse index strings - >>> pp = db_pretty_printer('dummy') - >>> print pp._istr2ilist('0,2,89,4') + >>> pp = DBPrettyPrinter('dummy') + >>> pp._istr2ilist('0,2,89,4') [0, 2, 89, 4] - >>> print pp._istr2ilist('1:6') + >>> pp._istr2ilist('1:6') [1, 2, 3, 4, 5] - >>> print pp._istr2ilist('0,3,6:9,2') + >>> pp._istr2ilist('0,3,6:9,2') [0, 3, 6, 7, 8, 2] """ ret = [] - for spl in index_string.split(',') : + for spl in index_string.split(','): s = spl.split(':') - if len(s) == 1 : + if len(s) == 1: ret.append(int(spl)) - elif len(s) == 2 : - for i in range(int(s[0]),int(s[1])) : + elif len(s) == 2: + for i in range(int(s[0]),int(s[1])): ret.append(i) - else : - raise indexStringError, "unrecognized index '%s'" % spl + else: + raise IndexStringError, "unrecognized index '%s'" % spl return ret - def _norm_width(self, width_in=None, active_fields=None, skinny=True) : + + def _norm_width(self, width_in=None, active_fields=None, skinny=True): "Normalize the width parameter" active_fields = self._norm_active_fields(active_fields) - if type(width_in) == type(1) or width_in == 'a' : # constant width + if isinstance(width_in, int) or width_in == 'a' : # constant width width = {} # set all fields to this width - for field in active_fields.keys() : + for field in active_fields.keys(): width[field] = width_in - else : - if width_in == None : + else: + if width_in == None: width_in = {} width = {} - for field in active_fields.keys() : - # fill in the gaps in the current width - if field in width_in : + for field in active_fields.keys(): + # fill in the gaps in the current width + if field in width_in: width[field] = width_in[field] else : # field doesn't exist if skinny : # set to a fixed width @@ -388,89 +412,96 @@ class db_pretty_printer (object) : else : # set to automatic width[field] = 'a' return width - def _norm_record_ids(self, record_ids=None) : + + def _norm_record_ids(self, record_ids=None): "Normalize the record_ids parameter" - if record_ids == None : + if record_ids == None: record_ids = range(len(self.db.records())) - if type(record_ids) == type('') : + if isinstance(record_ids, types.StringTypes): record_ids = self._istr2ilist(record_ids) stderr.flush() return record_ids + def _line_record_string(self, record, width=None, active_fields=None, - FS=None, RS=None, TRUNC_STRING=None) : + FS=None, RS=None, TRUNC_STRING=None): """ + Because doctest doesn't play well with tabs, use colons as field seps. - >>> db = text_db(FS=':', RS=' ; ', filename=None) - >>> pp = db_pretty_printer(db) + >>> db = TextDB(FS=':', RS=' ; ', filename=None) + + >>> pp = DBPrettyPrinter(db) >>> db._parse("#Name:Amount:CAS#:Vendor ; 2-Propanol:4 L:67-63-0:Fisher") - >>> print pp._line_record_string_id(0) - 2-Propa: 4 L:67-63-0: Fisher ; + >>> pp._line_record_string_id(0) + '2-Propa: 4 L:67-63-0: Fisher ; ' """ fields = self.db.field_list() active_fields = self._norm_active_fields(active_fields) width = self._norm_width(width) - if FS == None : + if FS == None: FS = self.db.FS - if RS == None : + if RS == None: RS = self.db.RS - for field in fields : - if field in active_fields and active_fields[field] : + for field in fields: + if field in active_fields and active_fields[field]: lastfield = field # generate the pretty-print string string = "" - for field in fields : - if field in active_fields and active_fields[field] : + for field in fields: + if field in active_fields and active_fields[field]: w = width[field] string += "%*.*s" % (w, w, record[field]) - if field != lastfield : + if field != lastfield: string += "%s" % (FS) string += RS return string + def _line_record_string_id(self, id, width=None, active_fields=None, - FS=None, RS=None, TRUNC_STRING=None) : + FS=None, RS=None, TRUNC_STRING=None): return self._line_record_string(self.db.record(id), width, active_fields, FS, RS, TRUNC_STRING) - def _get_field_width(self, record_ids, field) : - """ - Return the width of the longest value in FIELD - for all the records with db_ids in record_ids. + + def _get_field_width(self, record_ids, field): + """Return the width of the longest value in FIELD for all the + records with db_ids in record_ids. """ width = 1 - for i in record_ids : + for i in record_ids: w = len(self.db.record(i)[field]) - if w > width : + if w > width: width = w return width - def _get_width(self, width_in, active_fields=None, record_ids=None) : - """ - Return the width of the largest value in FIELD - for all the records with db_ids in record_ids. + def _get_width(self, width_in, active_fields=None, record_ids=None): + """Return the width of the largest value in FIELD for all the + records with db_ids in record_ids. """ active_fields = self._norm_active_fields(active_fields) width = self._norm_width(width_in, active_fields) record_ids = self._norm_record_ids(record_ids) - for field in active_fields : - if width[field] == 'a' : + for field in active_fields: + if width[field] == 'a': width[field] = self._get_field_width(record_ids, field) return width + def multi_record_string(self, record_ids=None, active_fields=None, width=None, FS=None, RS=None, COM_CHAR=None, - TRUNC_STRING=None) : + TRUNC_STRING=None): """ + Because doctest doesn't play well with tabs, use colons as field seps. - >>> db = text_db(FS=':', RS=' ; ', filename=None) - >>> pp = db_pretty_printer(db) + >>> db = TextDB(FS=':', RS=' ; ', filename=None) + + >>> pp = DBPrettyPrinter(db) >>> db._parse("#Name:Amount:CAS#:Vendor ; 2-Propanol:4 L:67-63-0:Fisher") - >>> print pp.multi_record_string('0'), - Name: Amount: CAS#: Vendor ; 2-Propa: 4 L:67-63-0: Fisher ; + >>> pp.multi_record_string('0') + ' Name: Amount: CAS#: Vendor ; 2-Propa: 4 L:67-63-0: Fisher ; ' """ - if FS == None : + if FS == None: FS = self.db.FS - if RS == None : + if RS == None: RS = self.db.RS - if COM_CHAR == None : + if COM_CHAR == None: COM_CHAR = self.db.COM_CHAR active_fields = self._norm_active_fields(active_fields) record_ids = self._norm_record_ids(record_ids) @@ -484,7 +515,7 @@ class db_pretty_printer (object) : active_fields, FS, RS, TRUNC_STRING=TRUNC_STRING) # print the records - for id in record_ids : + for id in record_ids: string += self._line_record_string_id(id, width, active_fields, FS, RS, TRUNC_STRING=TRUNC_STRING) @@ -494,6 +525,6 @@ class db_pretty_printer (object) : def _test(): import doctest doctest.testmod() - -if __name__ == "__main__" : + +if __name__ == "__main__": _test() diff --git a/chemdb/server.py b/chemdb/server.py new file mode 100644 index 0000000..9905630 --- /dev/null +++ b/chemdb/server.py @@ -0,0 +1,372 @@ +# Copyright + +"""Chemical inventory web interface. +""" + +from __future__ import with_statement + +from cgi import escape +import os +import os.path +import re +import sys, logging + +import cherrypy +from jinja2 import Environment, FileSystemLoader + +from .daemon import Daemon +from .db.text import TextDB +from .chemdb import valid_CASno, MSDSManager, DocGen + + +__version__ = "0.4" + + +class Server (object): + """ChemDB web interface.""" + def __init__(self, db=None, MSDS_manager=None, docs=None, + template_root='template', static_dir='static', + static_url='static'): + self.db = db + self.MSDS_manager = MSDS_manager + self.docs = docs + self.static_dir = static_dir + self.static_url = static_url + self.env = Environment(loader=FileSystemLoader(template_root)) + self.width_max = {'CAS#':12} + self.entry_width = 50 # display width of entry fields + self.raw_fields = ['ID','Name'] + self.MSDS_content_types = [ + 'text/plain', 'text/html', 'application/pdf'] + + @cherrypy.expose + def index(self, id=None): + """Chemical index page. + """ + self.db._refresh() + if id == None: + return self._index_page() + else: + return self._view_page(id=id) + + def _index_page(self): + records = self.db.records() + for record in records: + for field in self.db.field_list(): + rstring = record[field] + if field in self.width_max: # truncate if width is regulated... + w = self.width_max[field] + if len(rstring) > w: # ... and full string is too long. + rstring = "%s..." % rstring[:w-3] + # if the field isn't raw, protect special chars + if not field in self.raw_fields: + rstring = escape(rstring) + if self.MSDS_manager.has_MSDS(record['db_id']): + # link the id to the MSDS + record['Name'] = ( + '%s' + % (self._MSDS_path(record['db_id']), record['Name'])) + template = self.env.get_template('index.html') + return template.render(fields=self.db.field_list(), records=records) + + def _view_page(self, id): + db_id = int(id) + record = self.db.record(db_id) + MSDS_link = None + if self.MSDS_manager.has_MSDS(db_id): + path = self._MSDS_path(db_id) + MSDS_link = '%s' % ( + path, os.path.basename(path)) + template = self.env.get_template('record.html') + return template.render(fields=self.db.field_list(), + long_fields=self.db.long_fields(), + record=record, + MSDS=MSDS_link, + escape=escape) + + def _MSDS_path(self, db_id): + path = self.MSDS_manager.get_MSDS_path(db_id) + path = os.path.relpath(path, self.static_dir) + path = os.path.join(self.static_url, path) + return path + + @cherrypy.expose + def edit(self, id=None, **kwargs): + """Render the edit-record.html template for the specified record. + """ + self.db._refresh() + if kwargs: + self._update_record(id=id, **kwargs) + raise cherrypy.HTTPRedirect(u'.?id=%s' % id, status=303) + MSDSs = self.MSDS_manager.get_all(simlinks=False) + if id in [None, '-1']: + record = dict([(field,'') for field in self.db.field_list()]) + record['db_id'] = '-1' + record['ID'] = str(record['db_id']) + else: + db_id = int(id) + record = self.db.record(db_id) + if self.MSDS_manager.has_MSDS(db_id): + MSDSs = None # only ask for an MSDS if we still need one + template = self.env.get_template('edit-record.html') + return template.render(fields=self.db.field_list(), + long_fields=self.db.long_fields(), + record=record, + MSDSs=MSDSs, + entry_width=self.entry_width, + escape=escape) + + def _update_record(self, id=None, **kwargs): + """Update a record with form input. + """ + self.db._refresh() + if id in [None, '-1']: + record = self.db.new_record() + logging.info('new record %s' % record['db_id']) + else: + db_id = int(id) + record = self.db.record(db_id) + update = False + for field in self.db.field_list(): + if kwargs[field] != record[field]: + # TODO: add validation! + update = True + record[field] = kwargs[field] + if kwargs.get('MSDS source', None) == 'upload': + # Handle any MSDS file actions + f = kwargs['MSDS upload'] + contents = f.file.read() + if len(contents) > 0 and f.type in self.MSDS_content_types: + self.MSDS_manager.save(int(record['ID']), contents, f.type) + elif kwargs.get('MSDS source', None) == 'share': + logging.info('linking MSDS %d to %d' + % (int(record['ID']), + int(kwargs['MSDS share'])) ) + self.MSDS_manager.link(int(record['ID']), + int(kwargs['MSDS share'])) + if update: + self.db.set_record(record['db_id'], record, backup=True) + + +class Docs (object): + "Generate and serve assorted official documents." + def __init__(self, db=None, docgen=None, template_root='template'): + self.db = db + self.docgen = docgen + self.namewidth = 40 + self.env = Environment(loader=FileSystemLoader(template_root)) + + @cherrypy.expose + def index(self): + """List the available documents. + """ + template = self.env.get_template('docs.html') + return template.render() + + @cherrypy.expose + def inventory_pdf(self): + self.db._refresh() + path = self.docgen.inventory(namewidth=self.namewidth) + cherrypy.response.headers['Content-Type'] = 'application/pdf' + return file(path, 'rb').read() + + @cherrypy.expose + def door_warning_pdf(self, location=None): + self.db._refresh() + regexp = re.compile(location, re.I) # Case insensitive + path = dgen.door_warning(lambda r: regexp.match(r['Location'])) + cherrypy.response.headers['Content-Type'] = 'application/pdf' + return file(path, 'rb').read() + + +class ServerDaemon (Daemon): + def __init__(self): + super(ServerDaemon, self).__init__() + self.gid = None + self.uid = None + self.pidfile = './chem_web.pid' + self.logfile = './chem_web.log' + self.loglevel = 'INFO' + + def run(self): + if cherrypy.__version__.startswith('3.'): + cherrypy.quickstart(root=self.server, config=self.app_config) + elif cherrypy.__version__.startswith('2.'): + cherrypy.server.start() + +# if self.pkey_file == None or self.cert_file == None: +# logging.info("http://%s:%d/" % web.validip(self.ip_address)) +# else: +# logging.info("https://%s:%d/" % web.validip(self.ip_address)) +# +# webpy_func = web.webpyfunc(urls, globals(), False) +# wsgi_func = web.wsgifunc(webpy_func) +# web.httpserver.runsimple(wsgi_func, +# web.validip(self.ip_address), +# ssl_private_key_filename=self.pkey_file, +# ssl_certificate_filename=self.cert_file) + + def read_basic_config(self): + pass + + def parse_options(self): + from optparse import OptionParser + + usage_string = ('%prog [options]\n' + '\n' + '2008, W. Trevor King.\n') + version_string = '%%prog %s' % __version__ + p = OptionParser(usage=usage_string, version=version_string) + + # Non-server options + p.add_option('-t', '--test', dest='test', default=False, + action='store_true', help='Run internal tests and exit.') + + # Daemon options + p.add_option('--start', dest='action', + action='store_const', const='start', default='start', + help='Start the daemon (the default action).') + p.add_option('--stop', dest='action', + action='store_const', const='stop', default='start', + help='Stop the daemon.') + p.add_option('-n', '--nodaemon', dest='daemonize', + action='store_false', default=True, + help='Run in the foreground.') + + # Server options + p.add_option('-a', '--address', dest='address', default='127.0.0.1', + metavar='ADDR', + help='Address that the server will bind to (%default).') + p.add_option('-p', '--port', dest='port', default='8080', + metavar='PORT', + help='Port that the server will listen on (%default).') + p.add_option('-s', '--secure', dest="secure", + help="Run in secure (HTTPS) mode.", + type='string', metavar="PKEY_FILE:CERT_FILE") + p.add_option('-v', '--verbose', dest="verbose", action="store_true", + help="Print lots of debugging information.", + default=False) + p.add_option('--static', dest='static', metavar='PATH', + help="Path to the directory of static files (%default).", + default=os.path.join('example', 'static')) + p.add_option('--template', dest='template', metavar='PATH', + help="Path to the directory of template files (%default).", + default=os.path.join('template', 'web')) + p.add_option('--doc', dest='doc', metavar='PATH', + help="Path to the directory of document generation files (%default).", + default=os.path.join('template', 'doc')) + p.add_option('--htaccess', dest='htaccess', metavar='FILE', + help="Path to the htaccess file (%default).", + default='.htaccess') + + # Database options + p.add_option('--database', dest='database', metavar='FILE', + help="Path to the database file (%default).", + default=os.path.join('example', 'inventory.db')) + + self.options, args = p.parse_args() + p.destroy() + + if self.options.test == True: + _test() + sys.exit(0) + + if self.options.verbose: + self.loglevel = 'DEBUG' + + # get self.options for httpserver + if self.options.secure != None: + split = self.options.secure.split(':', 1) + assert len(split) == 2, ( + "Invalid secure argument '%s'" % self.options.secure) + self.pkey_file = split[0] + self.cert_file = split[1] + + # HACK! to ensure we *always* get utf-8 output + #reload(sys) + #sys.setdefaultencoding('utf-8') + + dirname,filename = os.path.split( + os.path.abspath(self.options.database)) + static_dir = os.path.abspath(self.options.static) + MSDS_dir = os.path.join(static_dir, 'MSDS') + template_dir = os.path.abspath(self.options.template) + doc_dir = os.path.abspath(self.options.doc) + db = TextDB(filename=filename, current_dir=dirname) + MSDS_manager = MSDSManager(db=db, dir=MSDS_dir) + docgen = DocGen(db=db, doc_root=doc_dir) + docs = Docs(db=db, docgen=docgen, template_root=template_dir) + server = Server(db=db, MSDS_manager=MSDS_manager, docs=docs, + template_root=template_dir, static_dir=static_dir, + static_url='/static') + + if cherrypy.__version__.startswith('3.'): + cherrypy.config.update({ # http://www.cherrypy.org/wiki/ConfigAPI + 'server.socket_host': self.options.address, + 'server.socket_port': int(self.options.port), + 'tools.decode.on': True, + 'tools.encode.on': True, + 'tools.encode.encoding': 'utf8', + 'tools.staticdir.root': static_dir, + }) + digest_auth = None + if cherrypy.__version__.startswith('3.2'): + try: + get_ha1 = cherrypy.lib.auth_digest.get_ha1_file_htdigest( + self.options.htaccess) + except IOError: + pass + else: + digest_auth = { + 'tools.auth_digest.on': True, + 'tools.auth_digest.realm': 'cookbook', + 'tools.auth_digest.get_ha1': get_ha1, + 'tools.auth_digest.key': str(uuid.uuid4()), + } + else: + passwds = {} + try: + with open(self.options.htaccess, 'r') as f: + for line in f: + user,realm,ha1 = line.strip().split(':') + passwds[user] = ha1 # use the ha1 as the password + except IOError: + pass + else: + digest_auth = { + 'tools.digest_auth.on': True, + 'tools.digest_auth.realm': 'cookbook', + 'tools.digest_auth.users': passwds, + } + app_config = { + '/static': { + 'tools.staticdir.on': True, + 'tools.staticdir.dir': '', + }, + } + if digest_auth != None: + for url in ['edit']: + app_config[url] = digest_auth + self.server = server + self.app_config = app_config + elif cherrypy.__version__.startswith('2.'): + cherrypy.root = server + cherrypy.config.update({ + 'server.environment': 'production', + 'server.socket_host': self.options.address, + 'server.socket_port': int(self.options.port), + 'decoding_filter.on': True, + 'encoding_filter.on': True, + 'encodinf_filter.encoding': 'utf8', + 'static_filter.on': True, + 'static_filter.dir': static_dir, + }) + cherrypy.server.start() + else: + raise NotImplementedError( + 'Unsupported CherryPy version %s' % cherrypy.__version__) + + +def _test(): + import doctest + doctest.testmod() diff --git a/certgen.py b/contrib/ssl/certgen.py similarity index 100% rename from certgen.py rename to contrib/ssl/certgen.py diff --git a/mk_simple_certs.py b/contrib/ssl/mk_simple_certs.py old mode 100644 new mode 100755 similarity index 77% rename from mk_simple_certs.py rename to contrib/ssl/mk_simple_certs.py index ecff515..b8f4fca --- a/mk_simple_certs.py +++ b/contrib/ssl/mk_simple_certs.py @@ -1,10 +1,12 @@ +#!/usr/bin/python """ From pyOpenSSL examples with a bit of wrapping. Create certificates and private keys for the 'simple' example. """ from OpenSSL import crypto -from certgen import * # yes yes, I know, I'm lazy +import certgen + def get_cert_filenames(server_name) : """ @@ -22,9 +24,9 @@ def mk_certs(server_name) : """ pkey_file,cert_file = get_cert_filenames(server_name) - cakey = createKeyPair(TYPE_RSA, 1024) - careq = createCertRequest(cakey, CN='Certificate Authority') - cacert = createCertificate(careq, (careq, cakey), 0, (0, 60*60*24*365*5)) # five years + cakey = certgen.createKeyPair(certgen.TYPE_RSA, 1024) + careq = certgen.createCertRequest(cakey, CN='Certificate Authority') + cacert = certgen.createCertificate(careq, (careq, cakey), 0, (0, 60*60*24*365*5)) # five years open(pkey_file, 'w').write(crypto.dump_privatekey(crypto.FILETYPE_PEM, cakey)) open(cert_file, 'w').write(crypto.dump_certificate(crypto.FILETYPE_PEM, cacert)) diff --git a/examples/inventory.db b/example/inventory.db similarity index 100% rename from examples/inventory.db rename to example/inventory.db diff --git a/example/static/MSDS/0.html b/example/static/MSDS/0.html new file mode 100644 index 0000000..551e48c --- /dev/null +++ b/example/static/MSDS/0.html @@ -0,0 +1,7 @@ + + + + + Acetic Acid MSDS. + + diff --git a/docs/Makefile b/template/doc/Makefile similarity index 100% rename from docs/Makefile rename to template/doc/Makefile diff --git a/docs/README b/template/doc/README similarity index 100% rename from docs/README rename to template/doc/README diff --git a/docs/contact.tex b/template/doc/contact.tex similarity index 100% rename from docs/contact.tex rename to template/doc/contact.tex diff --git a/docs/door_template.tex b/template/doc/door_template.tex similarity index 100% rename from docs/door_template.tex rename to template/doc/door_template.tex diff --git a/docs/inventory_template.tex b/template/doc/inventory_template.tex similarity index 100% rename from docs/inventory_template.tex rename to template/doc/inventory_template.tex diff --git a/docs/mp/Makefile b/template/doc/mp/Makefile similarity index 100% rename from docs/mp/Makefile rename to template/doc/mp/Makefile diff --git a/docs/mp/NFPA_c.mp b/template/doc/mp/NFPA_c.mp similarity index 100% rename from docs/mp/NFPA_c.mp rename to template/doc/mp/NFPA_c.mp diff --git a/docs/mp/README b/template/doc/mp/README similarity index 100% rename from docs/mp/README rename to template/doc/mp/README diff --git a/docs/mp/gen_NFPA.sh b/template/doc/mp/gen_NFPA.sh similarity index 100% rename from docs/mp/gen_NFPA.sh rename to template/doc/mp/gen_NFPA.sh diff --git a/docs/mp/sample.tex b/template/doc/mp/sample.tex similarity index 100% rename from docs/mp/sample.tex rename to template/doc/mp/sample.tex diff --git a/template/web/base.html b/template/web/base.html new file mode 100644 index 0000000..dfd2abd --- /dev/null +++ b/template/web/base.html @@ -0,0 +1,34 @@ + + + + + ChemDB + + + + +
+ +
+

{% block page_title %}{% endblock %}

+ {% block content %}{% endblock %} +
+ +
+ + diff --git a/template/web/docs.html b/template/web/docs.html new file mode 100644 index 0000000..153c96a --- /dev/null +++ b/template/web/docs.html @@ -0,0 +1,35 @@ +{% extends "base.html" %} + +{% block page_title %} + Documents +{% endblock %} + +{% block content %} + +

+ For door warnings for subsections of the whole room, please give a + location regexp in the form below. For example: ".*liquids" or + "refrigerator". +

+
+ + + +
Location regexp:
+ +
+{% endblock %} diff --git a/template/web/edit-record.html b/template/web/edit-record.html new file mode 100644 index 0000000..6e5a5b7 --- /dev/null +++ b/template/web/edit-record.html @@ -0,0 +1,58 @@ +{% extends "base.html" %} + +{% block page_title %} + Edit {{ record['ID'] }} +{% endblock %} + +{% block content %} +

Editing: {{ record['ID'] }}

+ +
+ + + + + {% for field in fields %} + + + + + {% endfor %} + {% if MSDSs %} + + + + + + + + + + + + + {% endif %} +
FieldValue
+
+ Upload + Share +
+
+ +
+ +
+{% endblock %} diff --git a/template/web/index.html b/template/web/index.html new file mode 100644 index 0000000..5bff6ae --- /dev/null +++ b/template/web/index.html @@ -0,0 +1,39 @@ +{% extends "base.html" %} + +{% block page_title %} + Index +{% endblock %} + +{% block content %} +

See the + rules for more information. See + the docs page to generate required + documents. +

+

Add entry

+ {% if records %} + + + {% for field in fields %} + + {% endfor %} + + {% for record in records %} + + {% for field in fields %} + {% if field == 'ID' %} + + {% else %} + + {% endif %} + {% endfor %} + + {% endfor %} +
{{ field }}
+ + {{ record[field] }} + + {{ record[field] }}
+ {% endif %} +

Add entry

+{% endblock %} diff --git a/template/web/record.html b/template/web/record.html new file mode 100644 index 0000000..2be4e64 --- /dev/null +++ b/template/web/record.html @@ -0,0 +1,26 @@ +{% extends "base.html" %} + +{% block page_title %} + {{ record['ID'] }} +{% endblock %} + +{% block content %} +

{{ record['ID'] }}

+ + + + + {% for field in fields %} + + + + + {% endfor %} + + + + +
FieldValue
{{ escape(long_fields[field]) }}{{ escape(record[field]) }}
{{ MSDS }}
+

+ Edit record

+{% endblock %} diff --git a/update_copyright.py b/update_copyright.py new file mode 100755 index 0000000..60b929b --- /dev/null +++ b/update_copyright.py @@ -0,0 +1,621 @@ +#!/usr/bin/python +# +# Copyright (C) 2010 W. Trevor King +# +# This file is part of Cookbook. +# +# Cookbook is free software: you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the +# Free Software Foundation, either version 3 of the License, or (at your +# option) any later version. +# +# Cookbook is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with Cookbook. If not, see . + +"""Automatically update copyright boilerplate. + +This script is adapted from one written for `Bugs Everywhere`_. + +.. _Bugs Everywhere: http://bugseverywhere.org/ +""" + +import difflib +import email.utils +import os +import os.path +import re +import sys +import time + + +PROJECT_INFO = { + 'project': 'ChemDB', + 'vcs': 'Git', + } + +# Break "copyright" into "copy" and "right" to avoid matching the +# REGEXP. +COPY_RIGHT_TEXT=""" +This file is part of %(project)s. + +%(project)s is free software: you can redistribute it and/or modify it +under the terms of the GNU General Public License as published by the +Free Software Foundation, either version 3 of the License, or (at your +option) any later version. + +%(project)s is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with %(project)s. If not, see . +""".strip() + +COPY_RIGHT_TAG='-xyz-COPY' + '-RIGHT-zyx-' # unlikely to occur in the wild :p + +# Convert author names to canonical forms. +# ALIASES[] = +# for example, +# ALIASES = { +# 'John Doe ': +# ['John Doe', 'jdoe', 'J. Doe '], +# } +# Git-based projects are encouraged to use .mailmap instead of +# ALIASES. See git-shortlog(1) for details. +ALIASES = {} + +# List of paths that should not be scanned for copyright updates. +# IGNORED_PATHS = ['./.git/'] +IGNORED_PATHS = ['./.git/', './template/'] +# List of files that should not be scanned for copyright updates. +# IGNORED_FILES = ['COPYING'] +IGNORED_FILES = ['COPYING', 'certgen.py', 'mk_simple_certs.py', + 'daemon.py'] + +# Work around missing author holes in the VCS history. +# AUTHOR_HACKS[] = [] = +# for example, if module.py was published in 2008 but the VCS history +# only goes back to 2010: +# YEAR_HACKS = { +# ('path', 'to', 'module.py'):2008, +# } +YEAR_HACKS = {} + +# Helpers for VCS-specific commands + +def splitpath(path): + """Recursively split a path into elements. + + Examples + -------- + + >>> splitpath(os.path.join('a', 'b', 'c')) + ('a', 'b', 'c') + >>> splitpath(os.path.join('.', 'a', 'b', 'c')) + ('a', 'b', 'c') + """ + path = os.path.normpath(path) + elements = [] + while True: + dirname,basename = os.path.split(path) + elements.insert(0,basename) + if dirname in ['', '.']: + break + path = dirname + return tuple(elements) + +# VCS-specific commands + +if PROJECT_INFO['vcs'] == 'Git': + + import subprocess + + _MSWINDOWS = sys.platform == 'win32' + _POSIX = not _MSWINDOWS + + def invoke(args, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, expect=(0,)): + """ + expect should be a tuple of allowed exit codes. + """ + try : + if _POSIX: + q = subprocess.Popen(args, stdin=subprocess.PIPE, + stdout=stdout, stderr=stderr) + else: + assert _MSWINDOWS == True, 'invalid platform' + # win32 don't have os.execvp() so run the command in a shell + q = subprocess.Popen(args, stdin=subprocess.PIPE, + stdout=stdout, stderr=stderr, shell=True) + except OSError, e: + raise ValueError([args, e]) + stdout,stderr = q.communicate(input=stdin) + status = q.wait() + if status not in expect: + raise ValueError([args, status, stdout, stderr]) + return status, stdout, stderr + + def git_cmd(*args): + status,stdout,stderr = invoke(['git'] + list(args)) + return stdout.rstrip('\n') + + def original_year(filename, year_hacks=YEAR_HACKS): + output = git_cmd('log', '--follow', + '--format=format:%ad', # Author date + '--date=short', # YYYY-MM-DD + filename) + years = [int(line.split('-', 1)[0]) for line in output.splitlines()] + if splitpath(filename) in year_hacks: + years.append(year_hacks[splitpath(filename)]) + years.sort() + return years[0] + + def authors(filename, author_hacks=AUTHOR_HACKS): + output = git_cmd('log', '--follow', '--format=format:%aN <%aE>', + filename) # Author name + ret = list(set(output.splitlines())) + if splitpath(filename) in author_hacks: + ret.extend(author_hacks[splitpath(filename)]) + return ret + + def authors_list(author_hacks=AUTHOR_HACKS): + output = git_cmd('log', '--format=format:%aN <%aE>') + ret = list(set(output.splitlines())) + for path,authors in author_hacks.items(): + ret.extend(authors) + return ret + + def is_versioned(filename): + output = git_cmd('log', '--follow', filename) + if len(output) == 0: + return False + return True + +elif PROJECT_INFO['vcs'] == 'Mercurial': + + import StringIO + import mercurial + import mercurial.dispatch + + def mercurial_cmd(*args): + cwd = os.getcwd() + stdout = sys.stdout + stderr = sys.stderr + tmp_stdout = StringIO.StringIO() + tmp_stderr = StringIO.StringIO() + sys.stdout = tmp_stdout + sys.stderr = tmp_stderr + try: + mercurial.dispatch.dispatch(list(args)) + finally: + os.chdir(cwd) + sys.stdout = stdout + sys.stderr = stderr + return (tmp_stdout.getvalue().rstrip('\n'), + tmp_stderr.getvalue().rstrip('\n')) + + def original_year(filename, year_hacks=YEAR_HACKS): + # shortdate filter: YEAR-MONTH-DAY + output,error = mercurial_cmd('log', '--follow', + '--template', '{date|shortdate}\n', + filename) + years = [int(line.split('-', 1)[0]) for line in output.splitlines()] + if splitpath(filename) in year_hacks: + years.append(year_hacks[splitpath(filename)]) + years.sort() + return years[0] + + def authors(filename, author_hacks=AUTHOR_HACKS): + output,error = mercurial_cmd('log', '--follow', + '--template', '{author}\n', + filename) + ret = list(set(output.splitlines())) + if splitpath(filename) in author_hacks: + ret.extend(author_hacks[splitpath(filename)]) + return ret + + def authors_list(author_hacks=AUTHOR_HACKS): + output,error = mercurial_cmd('log', '--template', '{author}\n') + ret = list(set(output.splitlines())) + for path,authors in author_hacks.items(): + ret.extend(authors) + return ret + + def is_versioned(filename): + output,error = mercurial_cmd('log', '--follow', filename) + if len(error) > 0: + return False + return True + +elif PROJECT_INFO['vcs'] == 'Bazaar': + + import StringIO + import bzrlib + import bzrlib.builtins + import bzrlib.log + + class LogFormatter (bzrlib.log.LogFormatter): + supports_merge_revisions = True + preferred_levels = 0 + supports_deta = False + supports_tags = False + supports_diff = False + + def log_revision(self, revision): + raise NotImplementedError + + class YearLogFormatter (LogFormatter): + def log_revision(self, revision): + self.to_file.write( + time.strftime('%Y', time.gmtime(revision.rev.timestamp)) + +'\n') + + class AuthorLogFormatter (LogFormatter): + def log_revision(self, revision): + authors = revision.rev.get_apparent_authors() + self.to_file.write('\n'.join(authors)+'\n') + + def original_year(filename, year_hacks=YEAR_HACKS): + cmd = bzrlib.builtins.cmd_log() + cmd.outf = StringIO.StringIO() + cmd.run(file_list=[filename], log_format=YearLogFormatter, levels=0) + years = [int(year) for year in set(cmd.outf.getvalue().splitlines())] + if splitpath(filename) in year_hacks: + years.append(year_hacks[splitpath(filename)]) + years.sort() + return years[0] + + def authors(filename, author_hacks=AUTHOR_HACKS): + cmd = bzrlib.builtins.cmd_log() + cmd.outf = StringIO.StringIO() + cmd.run(file_list=[filename], log_format=AuthorLogFormatter, levels=0) + ret = list(set(cmd.outf.getvalue().splitlines())) + if splitpath(filename) in author_hacks: + ret.extend(author_hacks[splitpath(filename)]) + return ret + + def authors_list(author_hacks=AUTHOR_HACKS): + cmd = bzrlib.builtins.cmd_log() + cmd.outf = StringIO.StringIO() + cmd.run(log_format=AuthorLogFormatter, levels=0) + output = cmd.outf.getvalue() + ret = list(set(cmd.outf.getvalue().splitlines())) + for path,authors in author_hacks.items(): + ret.extend(authors) + return ret + + def is_versioned(filename): + cmd = bzrlib.builtins.cmd_log() + cmd.outf = StringIO.StringIO() + cmd.run(file_list=[filename]) + return True + +else: + raise NotImplementedError('Unrecognized VCS: %(vcs)s' % PROJECT_INFO) + +# General utility commands + +def _strip_email(*args): + """Remove email addresses from a series of names. + + Examples + -------- + + >>> _strip_email('J Doe ') + ['J Doe'] + >>> _strip_email('J Doe ', 'JJJ Smith ') + ['J Doe', 'JJJ Smith'] + """ + args = list(args) + for i,arg in enumerate(args): + if arg == None: + continue + author,addr = email.utils.parseaddr(arg) + args[i] = author + return args + +def _reverse_aliases(aliases): + """Reverse an `aliases` dict. + + Input: key: canonical name, value: list of aliases + Output: key: alias, value: canonical name + + Examples + -------- + + >>> aliases = { + ... 'J Doe ':['Johnny ', 'J'], + ... 'JJJ Smith ':['Jingly '], + ... None:['Anonymous '], + ... } + >>> r = _reverse_aliases(aliases) + >>> for item in sorted(r.items()): + ... print item + ('Anonymous ', None) + ('J', 'J Doe ') + ('Jingly ', 'JJJ Smith ') + ('Johnny ', 'J Doe ') + """ + output = {} + for canonical_name,_aliases in aliases.items(): + for alias in _aliases: + output[alias] = canonical_name + return output + +def _replace_aliases(authors, with_email=True, aliases=None): + """Consolidate and sort `authors`. + + Make the replacements listed in the `aliases` dict (key: canonical + name, value: list of aliases). If `aliases` is ``None``, default + to ``ALIASES``. + + >>> aliases = { + ... 'J Doe ':['Johnny '], + ... 'JJJ Smith ':['Jingly '], + ... None:['Anonymous '], + ... } + >>> _replace_aliases(['JJJ Smith ', 'Johnny ', + ... 'Jingly ', 'Anonymous '], + ... with_email=True, aliases=aliases) + ['J Doe ', 'JJJ Smith '] + >>> _replace_aliases(['JJJ Smith', 'Johnny', 'Jingly', 'Anonymous'], + ... with_email=False, aliases=aliases) + ['J Doe', 'JJJ Smith'] + >>> _replace_aliases(['JJJ Smith ', 'Johnny ', + ... 'Jingly ', 'J Doe '], + ... with_email=True, aliases=aliases) + ['J Doe ', 'JJJ Smith '] + """ + if aliases == None: + aliases = ALIASES + if with_email == False: + aliases = dict([(_strip_email(author)[0], _strip_email(*_aliases)) + for author,_aliases in aliases.items()]) + rev_aliases = _reverse_aliases(aliases) + for i,author in enumerate(authors): + if author in rev_aliases: + authors[i] = rev_aliases[author] + authors = sorted(list(set(authors))) + if None in authors: + authors.remove(None) + return authors + +def _copyright_string(original_year, final_year, authors, prefix=''): + """ + >>> print _copyright_string(original_year=2005, + ... final_year=2005, + ... authors=['A ', 'B '], + ... prefix='# ' + ... ) # doctest: +ELLIPSIS + # Copyright (C) 2005 A + # B + # + # This file... + >>> print _copyright_string(original_year=2005, + ... final_year=2009, + ... authors=['A ', 'B '] + ... ) # doctest: +ELLIPSIS + Copyright (C) 2005-2009 A + B + + This file... + """ + if original_year == final_year: + date_range = '%s' % original_year + else: + date_range = '%s-%s' % (original_year, final_year) + lines = ['Copyright (C) %s %s' % (date_range, authors[0])] + for author in authors[1:]: + lines.append(' '*(len('Copyright (C) ')+len(date_range)+1) + + author) + lines.append('') + lines.extend((COPY_RIGHT_TEXT % PROJECT_INFO).splitlines()) + for i,line in enumerate(lines): + lines[i] = (prefix + line).rstrip() + return '\n'.join(lines) + +def _tag_copyright(contents): + """ + >>> contents = '''Some file + ... bla bla + ... # Copyright (copyright begins) + ... # (copyright continues) + ... # bla bla bla + ... (copyright ends) + ... bla bla bla + ... ''' + >>> print _tag_copyright(contents).replace('COPY-RIGHT', 'CR') + Some file + bla bla + -xyz-CR-zyx- + (copyright ends) + bla bla bla + + """ + lines = [] + incopy = False + for line in contents.splitlines(): + if incopy == False and line.startswith('# Copyright'): + incopy = True + lines.append(COPY_RIGHT_TAG) + elif incopy == True and not line.startswith('#'): + incopy = False + if incopy == False: + lines.append(line.rstrip('\n')) + return '\n'.join(lines)+'\n' + +def _update_copyright(contents, original_year, authors): + """ + >>> contents = '''Some file + ... bla bla + ... # Copyright (copyright begins) + ... # (copyright continues) + ... # bla bla bla + ... (copyright ends) + ... bla bla bla + ... ''' + >>> print _update_copyright(contents, 2008, ['Jack', 'Jill'] + ... ) # doctest: +ELLIPSIS, +REPORT_UDIFF + Some file + bla bla + # Copyright (C) 2008-... Jack + # Jill + # + # This file... + (copyright ends) + bla bla bla + + """ + current_year = time.gmtime()[0] + copyright_string = _copyright_string( + original_year, current_year, authors, prefix='# ') + contents = _tag_copyright(contents) + return contents.replace(COPY_RIGHT_TAG, copyright_string) + +def ignored_file(filename, ignored_paths=None, ignored_files=None, + check_disk=True, check_vcs=True): + """ + >>> ignored_paths = ['./a/', './b/'] + >>> ignored_files = ['x', 'y'] + >>> ignored_file('./a/z', ignored_paths, ignored_files, False, False) + True + >>> ignored_file('./ab/z', ignored_paths, ignored_files, False, False) + False + >>> ignored_file('./ab/x', ignored_paths, ignored_files, False, False) + True + >>> ignored_file('./ab/xy', ignored_paths, ignored_files, False, False) + False + >>> ignored_file('./z', ignored_paths, ignored_files, False, False) + False + """ + if ignored_paths == None: + ignored_paths = IGNORED_PATHS + if ignored_files == None: + ignored_files = IGNORED_FILES + if check_disk == True and os.path.isfile(filename) == False: + return True + for path in ignored_paths: + if filename.startswith(path): + return True + if os.path.basename(filename) in ignored_files: + return True + if check_vcs == True and is_versioned(filename) == False: + return True + return False + +def _set_contents(filename, contents, original_contents=None, dry_run=False, + verbose=0): + if original_contents == None and os.path.isfile(filename): + f = open(filename, 'r') + original_contents = f.read() + f.close() + if verbose > 0: + print "checking %s ... " % filename, + if contents != original_contents: + if verbose > 0: + if original_contents == None: + print "[creating]" + else: + print "[updating]" + if verbose > 1 and original_contents != None: + print '\n'.join( + difflib.unified_diff( + original_contents.splitlines(), contents.splitlines(), + fromfile=os.path.normpath(os.path.join('a', filename)), + tofile=os.path.normpath(os.path.join('b', filename)), + n=3, lineterm='')) + if dry_run == False: + f = file(filename, 'w') + f.write(contents) + f.close() + elif verbose > 0: + print "[no change]" + +# Update commands + +def update_authors(authors_fn=authors_list, dry_run=False, verbose=0): + authors = authors_fn() + authors = _replace_aliases(authors, with_email=True, aliases=ALIASES) + new_contents = '%s was written by:\n%s\n' % ( + PROJECT_INFO['project'], + '\n'.join(authors) + ) + _set_contents('AUTHORS', new_contents, dry_run=dry_run, verbose=verbose) + +def update_file(filename, original_year_fn=original_year, authors_fn=authors, + dry_run=False, verbose=0): + f = file(filename, 'r') + contents = f.read() + f.close() + + original_year = original_year_fn(filename) + authors = authors_fn(filename) + authors = _replace_aliases(authors, with_email=True, aliases=ALIASES) + + new_contents = _update_copyright(contents, original_year, authors) + _set_contents(filename, contents=new_contents, original_contents=contents, + dry_run=dry_run, verbose=verbose) + +def update_files(files=None, dry_run=False, verbose=0): + if files == None or len(files) == 0: + files = [] + for dirpath,dirnames,filenames in os.walk('.'): + for filename in filenames: + files.append(os.path.join(dirpath, filename)) + + for filename in files: + if ignored_file(filename) == True: + continue + update_file(filename, dry_run=dry_run, verbose=verbose) + +def test(): + import doctest + doctest.testmod() + +if __name__ == '__main__': + import optparse + import sys + + usage = """%%prog [options] [file ...] + +Update copyright information in source code with information from +the %(vcs)s repository. Run from the %(project)s repository root. + +Replaces every line starting with '^# Copyright' and continuing with +'^#' with an auto-generated copyright blurb. If you want to add +#-commented material after a copyright blurb, please insert a blank +line between the blurb and your comment, so the next run of +``update_copyright.py`` doesn't clobber your comment. + +If no files are given, a list of files to update is generated +automatically. +""" % PROJECT_INFO + p = optparse.OptionParser(usage) + p.add_option('--test', dest='test', default=False, + action='store_true', help='Run internal tests and exit') + p.add_option('--dry-run', dest='dry_run', default=False, + action='store_true', help="Don't make any changes") + p.add_option('-v', '--verbose', dest='verbose', default=0, + action='count', help='Increment verbosity') + options,args = p.parse_args() + + if options.test == True: + test() + sys.exit(0) + + update_authors(dry_run=options.dry_run, verbose=options.verbose) + update_files(files=args, dry_run=options.dry_run, verbose=options.verbose) -- 2.26.2