From: david Date: Mon, 24 Dec 2012 01:39:26 +0000 (+2000) Subject: v9 of batch tagging X-Git-Url: http://git.tremily.us/gitweb.cgi?a=commitdiff_plain;h=32806b11e342834931bd4d9576f248cfe17ea952;p=notmuch-archives.git v9 of batch tagging --- diff --git a/aa/91b34bc40b6b1abad68dca52c423e8e85e7c95 b/aa/91b34bc40b6b1abad68dca52c423e8e85e7c95 new file mode 100644 index 000000000..9858d34c8 --- /dev/null +++ b/aa/91b34bc40b6b1abad68dca52c423e8e85e7c95 @@ -0,0 +1,215 @@ +Return-Path: +X-Original-To: notmuch@notmuchmail.org +Delivered-To: notmuch@notmuchmail.org +Received: from localhost (localhost [127.0.0.1]) + by olra.theworths.org (Postfix) with ESMTP id 53235431FBF + for ; Sun, 23 Dec 2012 17:40:14 -0800 (PST) +X-Virus-Scanned: Debian amavisd-new at olra.theworths.org +X-Spam-Flag: NO +X-Spam-Score: 0 +X-Spam-Level: +X-Spam-Status: No, score=0 tagged_above=-999 required=5 tests=[none] + autolearn=disabled +Received: from olra.theworths.org ([127.0.0.1]) + by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024) + with ESMTP id KrKXEzMdKkt9 for ; + Sun, 23 Dec 2012 17:40:12 -0800 (PST) +Received: from tesseract.cs.unb.ca (tesseract.cs.unb.ca [131.202.240.238]) + (using TLSv1 with cipher AES256-SHA (256/256 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id 919E0431FCB + for ; Sun, 23 Dec 2012 17:40:02 -0800 (PST) +Received: from fctnnbsc30w-156034082078.dhcp-dynamic.fibreop.nb.bellaliant.net + ([156.34.82.78] helo=zancas.localnet) + by tesseract.cs.unb.ca with esmtpsa + (TLS1.0:DHE_RSA_AES_128_CBC_SHA1:16) (Exim 4.72) + (envelope-from ) id 1Tmx1K-0008Kj-SZ + for notmuch@notmuchmail.org; Sun, 23 Dec 2012 21:40:01 -0400 +Received: from bremner by zancas.localnet with local (Exim 4.80) + (envelope-from ) id 1Tmx1F-0002nD-C6 + for notmuch@notmuchmail.org; Sun, 23 Dec 2012 21:39:53 -0400 +From: david@tethera.net +To: notmuch@notmuchmail.org +Subject: v9 of batch tagging +Date: Sun, 23 Dec 2012 21:39:26 -0400 +Message-Id: <1356313183-9266-1-git-send-email-david@tethera.net> +X-Mailer: git-send-email 1.7.10.4 +X-Spam_bar: - +X-BeenThere: notmuch@notmuchmail.org +X-Mailman-Version: 2.1.13 +Precedence: list +List-Id: "Use and development of the notmuch mail system." + +List-Unsubscribe: , + +List-Archive: +List-Post: +List-Help: +List-Subscribe: , + +X-List-Received-Date: Mon, 24 Dec 2012 01:40:14 -0000 + +This obsoletes + + id:1356095307-22895-1-git-send-email-david@tethera.net + +The main changes since v8 are the rebasing against the notmuch-restore +fixes in master, and the rewrite of the query (pre)-processing +unhex_and_quote. This incorporates the changes of + + id:1356231570-28232-1-git-send-email-david@tethera.net + +and now handles '()' (cf. id:87a9t5p4dz.fsf@qmul.ac.uk) + +With respect to + +,---- +| Finally, I don't know if a query can contain a : without being a +| prefix query. If it can that could end up being misquoted. +`---- + +This is pretty easy to work around by encoding that :. I think unless +it is a problem in practice I prefer not to keep an explicity list of +prefixes here; recognizing prefixes should really be a service from +libnotmuch. + +I dropped two patches (strnspn and hex_invariant), but picked up a new +strtok variation. Probably the name strtok_len2 could be improved +(and I see there is a typo in the patch subject). + + [Patch v9 05/17] util/string-util: add a new string tokenized + +Finally I added a test for the new parenthesis handling. + +[Patch v9 17/17] test/tagging: add test for handling of parens + +Fixup wise, the tests needed to be adjusted a bit for () being delimiters, +and the man page as well. + +I added the fclose in id:87wqw9hf9a.fsf@oiva.home.nikula.org + +And I modified the return value per id:87zk15hi7f.fsf@oiva.home.nikula.org + +Here is the interdiff for unhex_and_quote: + +commit 67c6aee87db5c7da25529e1c0feb64e422abb4b7 +Author: David Bremner +Date: Sat Dec 22 22:49:02 2012 -0400 + + simplify unhex_and_quote, support parens + + the overgeneral definition of a prefix can be replaced by lower case + alphabetic, and still work fine with current notmuch query syntax. + + use () as delimiters in unhex_and_quote, preserve delimiters + +diff --git a/tag-util.c b/tag-util.c +index 6f62fe6..91f3603 100644 +--- a/tag-util.c ++++ b/tag-util.c +@@ -56,6 +56,21 @@ illegal_tag (const char *tag, notmuch_bool_t remove) + return NULL; + } + ++/* Factor out the boilerplate to append a token to the query string. ++ * For use in unhex_and_quote */ ++ ++static tag_parse_status_t ++append_tok (const char *tok, size_t tok_len, ++ const char *line_for_error, char **query_string) ++{ ++ ++ *query_string = talloc_strndup_append_buffer (*query_string, tok, tok_len); ++ if (*query_string == NULL) ++ return line_error (TAG_PARSE_OUT_OF_MEMORY, line_for_error, "aborting"); ++ ++ return TAG_PARSE_SUCCESS; ++} ++ + /* Input is a hex encoded string, presumed to be a query for Xapian. + * + * Space delimited tokens are decoded and quoted, with '*' and prefixes +@@ -67,45 +82,41 @@ unhex_and_quote (void *ctx, char *encoded, const char *line_for_error, + { + char *tok = encoded; + size_t tok_len = 0; ++ size_t delim_len = 0; + char *buf = NULL; + size_t buf_len = 0; + tag_parse_status_t ret = TAG_PARSE_SUCCESS; + + *query_string = talloc_strdup (ctx, ""); + +- while ((tok = strtok_len (tok + tok_len, " ", &tok_len)) != NULL) { ++ while ((tok = strtok_len2 (tok + tok_len + delim_len, " ()", ++ &tok_len, &delim_len)) != NULL) { + + size_t prefix_len; + char delim = *(tok + tok_len); + +- *(tok + tok_len++) = '\0'; ++ *(tok + tok_len) = '\0'; + +- prefix_len = hex_invariant (tok, tok_len); ++ /* The following matches a superset of prefixes currently ++ * used by notmuch */ ++ prefix_len = strspn (tok, "abcdefghijklmnopqrstuvwxyz"); + +- if ((strcmp (tok, "*") == 0) || prefix_len >= tok_len - 1) { ++ if ((strcmp (tok, "*") == 0) || prefix_len == tok_len) { + + /* pass some things through without quoting or decoding. + * Note for '*' this is mandatory. + */ + +- if (! (*query_string = talloc_asprintf_append_buffer ( +- *query_string, "%s%c", tok, delim))) { +- +- ret = line_error (TAG_PARSE_OUT_OF_MEMORY, +- line_for_error, "aborting"); +- goto DONE; +- } ++ ret = append_tok (tok, tok_len, line_for_error, query_string); ++ if (ret) goto DONE; + + } else { + /* potential prefix: one for ':', then something after */ +- if ((tok_len - prefix_len > 2) && *(tok + prefix_len) == ':') { +- if (! (*query_string = talloc_strndup_append (*query_string, +- tok, +- prefix_len + 1))) { +- ret = line_error (TAG_PARSE_OUT_OF_MEMORY, +- line_for_error, "aborting"); +- goto DONE; +- } ++ if ((tok_len - prefix_len >= 2) && *(tok + prefix_len) == ':') { ++ ret = append_tok (tok, prefix_len + 1, ++ line_for_error, query_string); ++ if (ret) goto DONE; ++ + tok += prefix_len + 1; + tok_len -= prefix_len + 1; + } +@@ -122,13 +133,15 @@ unhex_and_quote (void *ctx, char *encoded, const char *line_for_error, + goto DONE; + } + +- if (! (*query_string = talloc_asprintf_append_buffer ( +- *query_string, "%s%c", buf, delim))) { +- ret = line_error (TAG_PARSE_OUT_OF_MEMORY, +- line_for_error, "aborting"); +- goto DONE; +- } ++ ret = append_tok (buf, buf_len, line_for_error, query_string); ++ if (ret) goto DONE; + } ++ /* restore the string */ ++ *(tok + tok_len) = delim; ++ ++ /* copy any delimiters */ ++ ret = append_tok (tok + tok_len, delim_len, line_for_error, query_string); ++ if (ret) goto DONE; + } + + DONE: +