html2text.py: Python 2.5 compatibility, improve Unicode support

Add support for Python 2.5 (remove unicode_literals import which does
not seem to be necessary), check before using break_on_hyphens (without
this option in Python 2.5, the output is uglier though) and avoid the
'with' keyword.

While at it, fix reading Unicode text from file in Python 2 (tested
with: echo € | tools/html2text.py) and support reading from stdin using
the '-' filename.

Tested against Python 2.5.6, 2.6.6, 2.7.9, 3.2.6, 3.4.3 with the
commands from the previous html2text.py commit message, and additionally
with the Unicode character € as input (instead of the faq.py output).

Change-Id: I3de3f7a4e7cf7d702463c3a59758803843338a54
Reviewed-on: https://code.wireshark.org/review/7823
Reviewed-by: Peter Wu <peter@lekensteyn.nl>
Tested-by: Peter Wu <peter@lekensteyn.nl>
Petri-Dish: Peter Wu <peter@lekensteyn.nl>
Tested-by: Petri Dish Buildbot <buildbot-no-reply@wireshark.org>
Reviewed-by: Anders Broman <a.broman58@gmail.com>

1 files changed, 16 insertions, 13 deletions

diff --git a/tools/html2text.py b/tools/html2text.py
index 54180fabcf..3f81b191bb 100755
--- a/tools/html2text.py
+++ b/tools/html2text.py
@@ -20,8 +20,6 @@
 # along with this program; if not, write to the Free Software
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 
-from __future__ import unicode_literals
-
 __author__      = "Peter Wu <peter@lekensteyn.nl>"
 __copyright__   = "Copyright 2015, Peter Wu"
 __license__     = "GPL (v2 or later)"
@@ -68,8 +66,14 @@ class TextHTMLParser(HTMLParser):
         if self.list_item_prefix:
             initial_indent += self.list_item_prefix
             indent += '    '
-        wrapper = TextWrapper(width=66, break_on_hyphens=False,
-            initial_indent=initial_indent, subsequent_indent=indent)
+        kwargs = {
+            'width': 66,
+            'initial_indent': initial_indent,
+            'subsequent_indent': indent
+        }
+        if sys.version_info[0:2] >= (2, 6):
+            kwargs['break_on_hyphens'] = False
+        wrapper = TextWrapper(**kwargs)
         return '\n'.join(wrapper.wrap(text))
 
     def _commit_block(self, newline='\n\n'):
@@ -148,22 +152,21 @@ class TextHTMLParser(HTMLParser):
 
 def main():
     htmlparser = TextHTMLParser()
-    if len(sys.argv) > 1:
-        if sys.version_info[0] >= 3:
-            # Python 3: read file as utf-8
-            kwargs = { 'encoding': 'utf-8' }
-        else:
-            kwargs = {}
-        with open(sys.argv[1], **kwargs) as f:
-            for line in f:
-                htmlparser.feed(line)
+    if len(sys.argv) > 1 and sys.argv[1] != '-':
+        filename = sys.argv[1]
+        f = open(filename, 'rb')
     else:
+        filename = None
         f = sys.stdin
+    try:
         if hasattr(f, 'buffer'):
             # Access raw (byte) buffer in Python 3 instead of decoded one
             f = f.buffer
         # Read stdin as as Unicode string
         htmlparser.feed(f.read().decode('utf-8'))
+    finally:
+        if filename is not None:
+            f.close()
     htmlparser.close()
 
 if __name__ == '__main__':