Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Allow user specify input encoding and override what is specified by the file. Turn 0xa0 character into nbsp entity.

Browse Source
This commit is contained in:
John Schember 2011-04-17 19:28:04 -04:00
parent 05fc3eec93
commit c0cf0e91d4
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/calibre/ebooks/pdb/plucker/reader.py
View File

@ -523,6 +523,7 @@ class Reader(FormatReader):
paragraph_open = True paragraph_open = True
c = ord(d[offset]) c = ord(d[offset])
# PHTML "functions"
if c == 0x0: if c == 0x0:
offset += 1 offset += 1
c = ord(d[offset]) c = ord(d[offset])
@ -736,6 +737,8 @@ class Reader(FormatReader):
# Paragraph Offset (The Exact Link Modifier modifies a Paragraph Link or Targeted Paragraph Link function to specify an exact byte offset within the paragraph. This function must be followed immediately by the function it modifies). # Paragraph Offset (The Exact Link Modifier modifies a Paragraph Link or Targeted Paragraph Link function to specify an exact byte offset within the paragraph. This function must be followed immediately by the function it modifies).
elif c == 0x9a: elif c == 0x9a:
offset += 2 offset += 2
elif c == 0xa0:
html += ' '
else: else:
html += unichr(c) html += unichr(c)
offset += 1 offset += 1
@ -751,4 +754,4 @@ class Reader(FormatReader):
return html return html
def get_text_uid_encoding(self, uid): def get_text_uid_encoding(self, uid):
return self.uid_text_secion_encoding.get(uid, self.default_encoding) return self.options.input_encoding if self.options.input_encoding else self.uid_text_secion_encoding.get(uid, self.default_encoding)