ref: c7cc9ebe206d8d418462c08d10893cd4186538f5
parent: 3da5182804211e4f7a85d90d25717b492283d3d2
author: Werner Lemberg <[email protected]>
date: Tue Jun 25 03:24:02 EDT 2013
[docmaker] Recognise URLs. * src/tools/docmaker/tohtml.py (re_url): New regular expression. (make_html_para): Use it.
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+2013-06-25 Werner Lemberg <[email protected]>
+
+ [docmaker] Recognise URLs.
+
+ * src/tools/docmaker/tohtml.py (re_url): New regular expression.
+ (make_html_para): Use it.
+
2013-06-19 Werner Lemberg <[email protected]>
* Version 2.5.0.1 released.
--- a/src/tools/docmaker/tohtml.py
+++ b/src/tools/docmaker/tohtml.py
@@ -1,4 +1,4 @@
-# ToHTML (c) 2002, 2003, 2005, 2006, 2007, 2008
+# ToHTML (c) 2002, 2003, 2005-2008, 2013
# David Turner <[email protected]>
from sources import *
@@ -5,9 +5,44 @@
from content import *
from formatter import *
-import time
+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 )
+
+
# The following defines the HTML header used by all generated pages.
html_header_1 = """\
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
@@ -291,6 +326,8 @@
line = self.make_html_word( words[0] )
for word in words[1:]:
line = line + " " + self.make_html_word( word )
+ # handle hyperlinks
+ line = re_url.sub( r'<a href="\1">\1</a>', line )
# convert `...' quotations into real left and right single quotes
line = re.sub( r"(^|\W)`(.*?)'(\W|$)", \
r'\1‘\2’\3', \