ref: fad93267a250db53552a1d20ae5840118be5dc3d
parent: 8bdc40716ace308693a6c0e81bc8e4fcb12426dc
author: Werner Lemberg <[email protected]>
date: Tue Jun 25 06:41:37 EDT 2013
[docmaker] Code shuffling. * src/tools/docmaker/tohtml.py (re_url): Move regexp... * src/tools/docmaker/sources.py: ... to this file.
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,12 @@
2013-06-25 Werner Lemberg <[email protected]>
+ [docmaker] Code shuffling.
+
+ * src/tools/docmaker/tohtml.py (re_url): Move regexp...
+ * src/tools/docmaker/sources.py: ... to this file.
+
+2013-06-25 Werner Lemberg <[email protected]>
+
[docmaker] Remove unused functions.
* src/tools/docmaker/content.py (DocMarkup.get_start,
--- a/src/tools/docmaker/sources.py
+++ b/src/tools/docmaker/sources.py
@@ -1,4 +1,4 @@
-# Sources (c) 2002-2004, 2006-2009, 2012
+# Sources (c) 2002-2004, 2006-2009, 2012, 2013
# David Turner <[email protected]>
#
#
@@ -139,6 +139,42 @@
#
re_italic = re.compile( r"_(\w(\w|')*)_(.*)" ) # _italic_
re_bold = re.compile( r"\*(\w(\w|')*)\*(.*)" ) # *bold*
+
+#
+# this regular expression code to identify an URL has been taken from
+#
+# http://mail.python.org/pipermail/tutor/2002-September/017228.html
+#
+# (with slight modifications)
+#
+
+urls = r'(?:https?|telnet|gopher|file|wais|ftp)'
+ltrs = r'\w'
+gunk = r'/#~:.?+=&%@!\-'
+punc = r'.:?\-'
+any = "%(ltrs)s%(gunk)s%(punc)s" % { 'ltrs' : ltrs,+ 'gunk' : gunk,
+ 'punc' : punc }
+url = r"""
+ (
+ \b # start at word boundary
+ %(urls)s : # need resource and a colon
+ [%(any)s] +? # followed by one or more of any valid
+ # character, but be conservative and
+ # take only what you need to...
+ (?= # [look-ahead non-consumptive assertion]
+ [%(punc)s]* # either 0 or more punctuation
+ (?: # [non-grouping parentheses]
+ [^%(any)s] | $ # followed by a non-url char
+ # or end of the string
+ )
+ )
+ )
+ """ % {'urls' : urls,+ 'any' : any,
+ 'punc' : punc }
+
+re_url = re.compile( url, re.VERBOSE | re.MULTILINE )
#
# used to detect the end of commented source lines
--- a/src/tools/docmaker/tohtml.py
+++ b/src/tools/docmaker/tohtml.py
@@ -5,42 +5,7 @@
from content import *
from formatter import *
-import time, re
-
-
-# this regular expression code to identify an URL has been taken from
-#
-# http://mail.python.org/pipermail/tutor/2002-September/017228.html
-#
-# (with slight modifications)
-
-urls = r'(?:https?|telnet|gopher|file|wais|ftp)'
-ltrs = r'\w'
-gunk = r'/#~:.?+=&%@!\-'
-punc = r'.:?\-'
-any = "%(ltrs)s%(gunk)s%(punc)s" % { 'ltrs' : ltrs,- 'gunk' : gunk,
- 'punc' : punc }
-url = r"""
- (
- \b # start at word boundary
- %(urls)s : # need resource and a colon
- [%(any)s] +? # followed by one or more of any valid
- # character, but be conservative and
- # take only what you need to...
- (?= # [look-ahead non-consumptive assertion]
- [%(punc)s]* # either 0 or more punctuation
- (?: # [non-grouping parentheses]
- [^%(any)s] | $ # followed by a non-url char
- # or end of the string
- )
- )
- )
- """ % {'urls' : urls,- 'any' : any,
- 'punc' : punc }
-
-re_url = re.compile( url, re.VERBOSE | re.MULTILINE )
+import time
# The following defines the HTML header used by all generated pages.