Implement #1428 (Suppress source file page breaks.)

This commit is contained in:
Kovid Goyal 2009-01-12 17:06:04 -08:00
parent 71dea7b4ee
commit d4e3104157
2 changed files with 2 additions and 2 deletions

View File

@ -335,7 +335,7 @@ class PreProcessor(object):
# Fix pdftohtml markup
PDFTOHTML = [
# Remove <hr> tags
(re.compile(r'<hr.*?>', re.IGNORECASE), lambda match: '<span style="page-break-after:always"> </span>'),
(re.compile(r'<hr.*?>', re.IGNORECASE), lambda match: '<br />'),
# Remove page numbers
(re.compile(r'\d+<br>', re.IGNORECASE), lambda match: ''),
# Remove <br> and replace <br><br> with <p>

View File

@ -122,7 +122,7 @@ class HTMLConverter(object, LoggingInterface):
# Fix pdftohtml markup
PDFTOHTML = [
# Remove <hr> tags
(re.compile(r'<hr.*?>', re.IGNORECASE), lambda match: '<span style="page-break-after:always"> </span>'),
(re.compile(r'<hr.*?>', re.IGNORECASE), lambda match: '<br />'),
# Remove page numbers
(re.compile(r'\d+<br>', re.IGNORECASE), lambda match: ''),
# Remove <br> and replace <br><br> with <p>