[docmaker] Code shuffling.

* src/tools/docmaker/tohtml.py (re_url): Move regexp...
* src/tools/docmaker/sources.py: ... to this file.
This commit is contained in:
Werner Lemberg 2013-06-25 10:41:37 +02:00
parent 8bdc40716a
commit fad93267a2
3 changed files with 45 additions and 37 deletions

View File

@ -1,3 +1,10 @@
2013-06-25 Werner Lemberg <wl@gnu.org>
[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 <wl@gnu.org>
[docmaker] Remove unused functions.

View File

@ -1,4 +1,4 @@
# Sources (c) 2002-2004, 2006-2009, 2012
# Sources (c) 2002-2004, 2006-2009, 2012, 2013
# David Turner <david@freetype.org>
#
#
@ -140,6 +140,42 @@ re_crossref = re.compile( r'@((?:\w|-)*)(.*)' )
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
#

View File

@ -5,42 +5,7 @@ from sources import *
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.