Fix for when 'trailer' is indented (#513)
* Fix for when 'trailer' is indented Closes #214 * Address CR comments - strip line after parsing * Update CHANGELOG.md Co-authored-by: Pieter Marsman <pietermarsman@gmail.com>pull/522/head^2
parent
61300eef70
commit
ec223d1f1d
|
@ -31,6 +31,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
|
||||||
### Fixed
|
### Fixed
|
||||||
- Rename PDFTextExtractionNotAllowedError to PDFTextExtractionNotAllowed to revert breaking change ([#461](https://github.com/pdfminer/pdfminer.six/pull/461))
|
- Rename PDFTextExtractionNotAllowedError to PDFTextExtractionNotAllowed to revert breaking change ([#461](https://github.com/pdfminer/pdfminer.six/pull/461))
|
||||||
- Always try to get CMap, not only for identity encodings ([#438](https://github.com/pdfminer/pdfminer.six/pull/438))
|
- Always try to get CMap, not only for identity encodings ([#438](https://github.com/pdfminer/pdfminer.six/pull/438))
|
||||||
|
- Recognizing 'trailer' keyword with spaces as prefix or suffix ([#513](https://github.com/pdfminer/pdfminer.six/pull/513))
|
||||||
|
|
||||||
## [20200720]
|
## [20200720]
|
||||||
|
|
||||||
|
|
|
@ -93,16 +93,15 @@ class PDFXRef(PDFBaseXRef):
|
||||||
while True:
|
while True:
|
||||||
try:
|
try:
|
||||||
(pos, line) = parser.nextline()
|
(pos, line) = parser.nextline()
|
||||||
if not line.strip():
|
line = line.strip()
|
||||||
|
if not line:
|
||||||
continue
|
continue
|
||||||
except PSEOF:
|
except PSEOF:
|
||||||
raise PDFNoValidXRef('Unexpected EOF - file corrupted?')
|
raise PDFNoValidXRef('Unexpected EOF - file corrupted?')
|
||||||
if not line:
|
|
||||||
raise PDFNoValidXRef('Premature eof: %r' % parser)
|
|
||||||
if line.startswith(b'trailer'):
|
if line.startswith(b'trailer'):
|
||||||
parser.seek(pos)
|
parser.seek(pos)
|
||||||
break
|
break
|
||||||
f = line.strip().split(b' ')
|
f = line.split(b' ')
|
||||||
if len(f) != 2:
|
if len(f) != 2:
|
||||||
error_msg = 'Trailer not found: {!r}: line={!r}'\
|
error_msg = 'Trailer not found: {!r}: line={!r}'\
|
||||||
.format(parser, line)
|
.format(parser, line)
|
||||||
|
@ -118,7 +117,7 @@ class PDFXRef(PDFBaseXRef):
|
||||||
(_, line) = parser.nextline()
|
(_, line) = parser.nextline()
|
||||||
except PSEOF:
|
except PSEOF:
|
||||||
raise PDFNoValidXRef('Unexpected EOF - file corrupted?')
|
raise PDFNoValidXRef('Unexpected EOF - file corrupted?')
|
||||||
f = line.strip().split(b' ')
|
f = line.split(b' ')
|
||||||
if len(f) != 3:
|
if len(f) != 3:
|
||||||
error_msg = 'Invalid XRef format: {!r}, line={!r}'\
|
error_msg = 'Invalid XRef format: {!r}, line={!r}'\
|
||||||
.format(parser, line)
|
.format(parser, line)
|
||||||
|
|
Loading…
Reference in New Issue