-
-
Notifications
You must be signed in to change notification settings - Fork 13
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #105 from mattip/v7.3.12
V7.3.12
- Loading branch information
Showing
16 changed files
with
611 additions
and
79 deletions.
There are no files selected for viewing
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,66 @@ | ||
| # HG changeset patch | ||
| # User Carl Friedrich Bolz-Tereick <[email protected]> | ||
| # Date 1689079860 -7200 | ||
| # Tue Jul 11 14:51:00 2023 +0200 | ||
| # Branch conda-3.9-v7.3.12 | ||
| # Node ID 163544ab2a142b8e7e040a098ec9013963c9fb64 | ||
| # Parent 3f3f2298ddc56db44bbdb4551ce992d8e9401646 | ||
| #3961: don't uselessly compile a regex for *every* parsed email message. the | ||
| pattern is anyway always the same, apart from a variable prefix. Instead, first | ||
| check the prefix with str.startswith, and only if that returns True, match the | ||
| rest of the regular expression. | ||
|
|
||
| diff -r 3f3f2298ddc5 -r 163544ab2a14 lib-python/3/email/feedparser.py | ||
| --- a/lib-python/3/email/feedparser.py Thu Jun 15 12:31:24 2023 +0300 | ||
| +++ b/lib-python/3/email/feedparser.py Tue Jul 11 14:51:00 2023 +0200 | ||
| @@ -37,6 +37,7 @@ | ||
| headerRE = re.compile(r'^(From |[\041-\071\073-\176]*:|[\t ])') | ||
| EMPTYSTRING = '' | ||
| NL = '\n' | ||
| +boundaryend_re = re.compile(r'(?P<end>--)?(?P<ws>[ \t]*)(?P<linesep>\r\n|\r|\n)?$') | ||
|
|
||
| NeedMoreData = object() | ||
|
|
||
| @@ -329,9 +330,14 @@ | ||
| # this onto the input stream until we've scanned past the | ||
| # preamble. | ||
| separator = '--' + boundary | ||
| - boundaryre = re.compile( | ||
| - '(?P<sep>' + re.escape(separator) + | ||
| - r')(?P<end>--)?(?P<ws>[ \t]*)(?P<linesep>\r\n|\r|\n)?$') | ||
| + # PyPy difference: don't compile a new regular expression for every | ||
| + # single message, instead just use str.startswith and a generic re | ||
| + # this prevents the JIT compiling more and more traces for all the | ||
| + # different (random) boundaries of messages | ||
| + def boundarymatch(line): | ||
| + if not line.startswith(separator): | ||
| + return None | ||
| + return boundaryend_re.match(line, len(separator)) | ||
| capturing_preamble = True | ||
| preamble = [] | ||
| linesep = False | ||
| @@ -343,7 +349,7 @@ | ||
| continue | ||
| if line == '': | ||
| break | ||
| - mo = boundaryre.match(line) | ||
| + mo = boundarymatch(line) | ||
| if mo: | ||
| # If we're looking at the end boundary, we're done with | ||
| # this multipart. If there was a newline at the end of | ||
| @@ -375,13 +381,13 @@ | ||
| if line is NeedMoreData: | ||
| yield NeedMoreData | ||
| continue | ||
| - mo = boundaryre.match(line) | ||
| + mo = boundarymatch(line) | ||
| if not mo: | ||
| self._input.unreadline(line) | ||
| break | ||
| # Recurse to parse this subpart; the input stream points | ||
| # at the subpart's first line. | ||
| - self._input.push_eof_matcher(boundaryre.match) | ||
| + self._input.push_eof_matcher(boundarymatch) | ||
| for retval in self._parsegen(): | ||
| if retval is NeedMoreData: | ||
| yield NeedMoreData |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,40 @@ | ||
| # HG changeset patch | ||
| # User Carl Friedrich Bolz-Tereick <[email protected]> | ||
| # Date 1689148718 -7200 | ||
| # Wed Jul 12 09:58:38 2023 +0200 | ||
| # Branch conda-3.9-v7.3.12 | ||
| # Node ID f371f05be18aedeeb966fd9b657e72a7dbbc5126 | ||
| # Parent 163544ab2a142b8e7e040a098ec9013963c9fb64 | ||
| #3961: precompile res in csv module | ||
|
|
||
| diff -r 163544ab2a14 -r f371f05be18a lib-python/3/csv.py | ||
| --- a/lib-python/3/csv.py Tue Jul 11 14:51:00 2023 +0200 | ||
| +++ b/lib-python/3/csv.py Wed Jul 12 09:58:38 2023 +0200 | ||
| @@ -162,6 +162,12 @@ | ||
| except NameError: | ||
| complex = float | ||
|
|
||
| +_SNIFFER_RES = [re.compile(restr, re.DOTALL | re.MULTILINE) for restr in | ||
| + (r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?", | ||
| + r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)', # ".*?", | ||
| + r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?" | ||
| + r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)')] # ".*?" (no delim, no space) | ||
| + | ||
| class Sniffer: | ||
| ''' | ||
| "Sniffs" the format of a CSV file (i.e. delimiter, quotechar) | ||
| @@ -214,11 +220,9 @@ | ||
| """ | ||
|
|
||
| matches = [] | ||
| - for restr in (r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?", | ||
| - r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)', # ".*?", | ||
| - r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?" | ||
| - r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)'): # ".*?" (no delim, no space) | ||
| - regexp = re.compile(restr, re.DOTALL | re.MULTILINE) | ||
| + # PyPy difference: compile the regular expressions only once, globally, | ||
| + # instead of on every call to sniff | ||
| + for regexp in _SNIFFER_RES: | ||
| matches = regexp.findall(data) | ||
| if matches: | ||
| break |
Oops, something went wrong.