commit b427ad8fbea4adbe4ba92324e80425981e54fbdb Author: Damian Johnson <atagar@torproject.org> Date: Sat Aug 16 15:37:14 2014 -0700 Using a constant for line regex we match against Just a minor tweak so the regex we use is with the others for descriptor content. --- docs/change_log.rst | 4 ++++ stem/descriptor/__init__.py | 6 ++++-- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/docs/change_log.rst b/docs/change_log.rst index 6789212..b52a377 100644 --- a/docs/change_log.rst +++ b/docs/change_log.rst @@ -40,6 +40,10 @@ Unreleased The following are only available within Stem's `git repository <download.html>`_. + * **Descriptors** + + * Improved speed for parsing consensus documents by around 30% (:trac:`12859`) + * **Utilities** * Added support for directories to :func:`stem.util.conf.Config.load`. diff --git a/stem/descriptor/__init__.py b/stem/descriptor/__init__.py index 411ad3d..c14d984 100644 --- a/stem/descriptor/__init__.py +++ b/stem/descriptor/__init__.py @@ -68,6 +68,7 @@ except ImportError: KEYWORD_CHAR = 'a-zA-Z0-9-' WHITESPACE = ' \t' KEYWORD_LINE = re.compile('^([%s]+)(?:[%s]+(.*))?$' % (KEYWORD_CHAR, WHITESPACE)) +SPECIFIC_KEYWORD_LINE = '^(%%s)(?:[%s]+(.*))?$' % WHITESPACE PGP_BLOCK_START = re.compile('^-----BEGIN ([%s%s]+)-----$' % (KEYWORD_CHAR, WHITESPACE)) PGP_BLOCK_END = '-----END %s-----' @@ -425,6 +426,7 @@ def _read_until_keywords(keywords, descriptor_file, inclusive = False, ignore_fi else: content = [] content_append = content.append + ending_keyword = None if isinstance(keywords, (bytes, unicode)): @@ -436,7 +438,7 @@ def _read_until_keywords(keywords, descriptor_file, inclusive = False, ignore_fi if first_line is not None: content_append(first_line) - match_re = re.compile(r'^(%s)(?:[ \t].*|)$' % "|".join(keywords)) + keyword_match = re.compile(SPECIFIC_KEYWORD_LINE % '|'.join(keywords)) while True: last_position = descriptor_file.tell() @@ -449,7 +451,7 @@ def _read_until_keywords(keywords, descriptor_file, inclusive = False, ignore_fi if not line: break # EOF - line_match = match_re.match(stem.util.str_tools._to_unicode(line)) + line_match = keyword_match.match(stem.util.str_tools._to_unicode(line)) if line_match: ending_keyword = line_match.groups()[0]