From e2a32e319871b3b639bf52f15f1c6a3d373432b1 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Fri, 29 Jun 2007 15:42:11 +0000
Subject: [PATCH] Another unicode bug squashed and improved <pre> handling

---
 src/libprs500/__init__.py                     |  2 +-
 src/libprs500/ebooks/lrf/html/convert_from.py | 12 +++++-------
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/src/libprs500/__init__.py b/src/libprs500/__init__.py
index 9ce0dc8ba3..9b02d8cef3 100644
--- a/src/libprs500/__init__.py
+++ b/src/libprs500/__init__.py
@@ -13,7 +13,7 @@
 ##    with this program; if not, write to the Free Software Foundation, Inc.,
 ##    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 ''' E-book management software'''
-__version__   = "0.3.61"
+__version__   = "0.3.62"
 __docformat__ = "epytext"
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 __appname__   = 'libprs500'
diff --git a/src/libprs500/ebooks/lrf/html/convert_from.py b/src/libprs500/ebooks/lrf/html/convert_from.py
index c4bbaaf8f5..96de6cc4c6 100644
--- a/src/libprs500/ebooks/lrf/html/convert_from.py
+++ b/src/libprs500/ebooks/lrf/html/convert_from.py
@@ -215,8 +215,6 @@ class Span(_Span):
             attrs.pop('fontfacename')
         _Span.__init__(self, text=src, **attrs)
         
-        
-        
 class HTMLConverter(object):
     SELECTOR_PAT   = re.compile(r"([A-Za-z0-9\-\_\:\.]+[A-Za-z0-9\-\_\:\.\s\,]*)\s*\{([^\}]*)\}")
     PAGE_BREAK_PAT = re.compile(r'page-break-(?:after|before)\s*:\s*(\w+)', re.IGNORECASE)
@@ -230,7 +228,7 @@ class HTMLConverter(object):
                          lambda match: match.group().replace('<!--', '').replace('-->', '')),
                          # remove <p> tags from within <a> tags
                         (re.compile(r'<a.*?>(.*?)</a\s*>', re.DOTALL|re.IGNORECASE),
-                         lambda match: re.compile(r'<.*?p.*?>', re.IGNORECASE).sub('', match.group())),
+                         lambda match: re.compile(r'<\s*?p.*?>', re.IGNORECASE).sub('', match.group())),
                          ]
     # Fix Baen markup
     BAEN_SANCTIFY = [(re.compile(r'<\s*[Aa]\s+id="p[0-9]+"\s+name="p[0-9]+"\s*>\s*<\/[Aa]>'), 
@@ -551,9 +549,9 @@ class HTMLConverter(object):
         cwd = os.getcwd()        
         for link in self.links:
             para, tag = link.para, link.tag
-            text = self.get_text(tag)
+            text = self.get_text(tag, 1000)
             # Needed for TOC entries due to bug in LRF
-            ascii_text = text.decode('utf8', 'replace').encode('ascii', 'replace')
+            ascii_text = text.encode('ascii', 'replace')
             if not text:
                 text = 'Link'
                 img = tag.find('img')
@@ -996,7 +994,7 @@ class HTMLConverter(object):
             lines = src.split('\n')
             for line in lines:
                 try:
-                    self.current_para.append(Span(line, tag_css, self.memory, self.profile.dpi, self.fonts))
+                    self.current_para.append(line)
                     self.current_para.CR()
                 except ConversionError:
                     pass
@@ -1375,7 +1373,7 @@ def console_query(dirpath, candidate, docs):
 def get_path(path, query=console_query):
     path = os.path.abspath(os.path.expanduser(path))
     ext = os.path.splitext(path)[1][1:].lower()
-    if ext in ['htm', 'html', 'xhtml']:
+    if ext in ['htm', 'html', 'xhtml', 'php']:
         return None, path
     dirpath = mkdtemp('','html2lrf')
     extract(path, dirpath)