Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
152d3aaf55 | ||
|
|
36a9371657 | ||
|
|
a29d465ea4 | ||
|
|
841576d9b8 | ||
|
|
bfc0b6ba34 | ||
|
|
336f5f1fba | ||
|
|
1b1db13b5b | ||
|
|
3f561f3488 | ||
|
|
989de3122e | ||
|
|
20be0aa49e |
No files matched your search
+3
-2
@@ -10,7 +10,8 @@ tests/*.txt
|
||||
.idea/
|
||||
.vscode
|
||||
tests/samples/output
|
||||
samples
|
||||
./samples
|
||||
**__pycache**\
|
||||
.mypy_cache
|
||||
.ipynb_checkpoints
|
||||
.ipynb_checkpoints
|
||||
venv
|
||||
+13
-7
@@ -4,10 +4,16 @@ WK_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
|
||||
cd $WK_DIR
|
||||
cd ..
|
||||
|
||||
for filename in ./tests/test*.py; do
|
||||
if python $filename ; then
|
||||
echo woohoo
|
||||
else
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
# for filename in ./tests/test*.py; do
|
||||
# if python $filename ; then
|
||||
# echo woohoo
|
||||
# else
|
||||
# exit 1
|
||||
# fi
|
||||
# done
|
||||
|
||||
if python ./test.py ; then
|
||||
echo "PASSED TESTS"
|
||||
else
|
||||
exit 1
|
||||
fi
|
||||
@@ -37,6 +37,7 @@ This generator-function yields individual pages which contain their respected it
|
||||
- `password`: [str](#) defaults to None
|
||||
- `caching`: [bool](#) defaults to True
|
||||
- `check_extractable`: [bool](#) defaults to True
|
||||
- `ignore_bad_chars`: [bool](#) defaults to False
|
||||
- `pagenos`: [List[int]](#) defaults to None
|
||||
- `debug_level`: [logging.levels](#https://docs.python.org/3/library/logging.html#levels) defaults logging.WARNING
|
||||
|
||||
|
||||
@@ -140,6 +140,7 @@ for page in PDFInterpreter("/path/to/pdf.pdf"):
|
||||
<li><code>password</code>: <a href="#">str</a> defaults to None </li>
|
||||
<li><code>caching</code>: <a href="#">bool</a> defaults to True </li>
|
||||
<li><code>check_extractable</code>: <a href="#">bool</a> defaults to True</li>
|
||||
<li><code>ignore_bad_chars</code>: <a href="#">bool</a> defaults to False</li>
|
||||
<li><code>pagenos</code>: <a href="#">List[int]</a> defaults to None</li>
|
||||
<li><code>debug_level</code>: <a href="#https://docs.python.org/3/library/logging.html#levels">logging.levels</a> defaults logging.WARNING</li>
|
||||
</ul>
|
||||
|
||||
+1
-1
@@ -240,5 +240,5 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.</p>
|
||||
|
||||
<!--
|
||||
MkDocs version : 1.0.4
|
||||
Build Date UTC : 2019-01-11 20:22:59
|
||||
Build Date UTC : 2019-12-08 19:44:26
|
||||
-->
|
||||
@@ -1 +1 @@
|
||||
{"config":{"lang":["en"],"prebuild_index":false,"separator":"[\\s\\-]+"},"docs":[{"location":"","text":"PDFMajor Latest Release PDF-Major is a fork of PDFMiner.six . It is meant to be a more light-weight implementation that makes fewer assumptions on the data. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon. Documentation See documentation here . Basic Example from pdfmajor.interpreter import PDFInterpreter for page in PDFInterpreter(\"/path/to/pdf.pdf\"): print(\"page start\", page.page_num) for item in page: print(\" >\", item) print(\"page end\", page.page_num) Why Another Fork? PDFMiner was designed to run in python 2.7>, PDFMiner.six was written to bring cross-version support for python 2 and 3. However, after attempting to build and extend upon PDFMiner.six I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports. Features Functional extraction method based on generators Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) Font-Color extraction Shape fill and stroke color extraction CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Note : We took out the layout-analysis process in this version (there is no more LTTextHorizontal or LTTextVertical). While the mathematics behind the grouping process was sound, the coupling of the layout-analysis process with the parsing and interpretation process produced unfriendly-code. This feature could be brought back by running your own implementation of it on the pdfmajor.interpreter.PageInterpreter class, but at the current time is not supported. How to Install Source Install Python 3.6.4 or newer. clone this repo git clone https://github.com/asosnovsky/pdfmajor * install repo python setup.py install Pypi Install Python 3.6.4 or newer. install repo pip install pdfmajor Terms and Conditions (This is so-called MIT/X License) Copyright (c) 2018-2019 Ariel Sosnovsky Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the \"Software\"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.","title":"Home"},{"location":"#pdfmajor","text":"Latest Release PDF-Major is a fork of PDFMiner.six . It is meant to be a more light-weight implementation that makes fewer assumptions on the data. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon.","title":"PDFMajor"},{"location":"#documentation","text":"See documentation here .","title":"Documentation"},{"location":"#basic-example","text":"from pdfmajor.interpreter import PDFInterpreter for page in PDFInterpreter(\"/path/to/pdf.pdf\"): print(\"page start\", page.page_num) for item in page: print(\" >\", item) print(\"page end\", page.page_num)","title":"Basic Example"},{"location":"#why-another-fork","text":"PDFMiner was designed to run in python 2.7>, PDFMiner.six was written to bring cross-version support for python 2 and 3. However, after attempting to build and extend upon PDFMiner.six I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports.","title":"Why Another Fork?"},{"location":"#features","text":"Functional extraction method based on generators Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) Font-Color extraction Shape fill and stroke color extraction CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Note : We took out the layout-analysis process in this version (there is no more LTTexLine truncated
|
||||
{"config":{"lang":["en"],"prebuild_index":false,"separator":"[\\s\\-]+"},"docs":[{"location":"","text":"PDFMajor Latest Release PDF-Major is a fork of PDFMiner.six . It is meant to be a more light-weight implementation that makes fewer assumptions on the data. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon. Documentation See documentation here . Basic Example from pdfmajor.interpreter import PDFInterpreter for page in PDFInterpreter(\"/path/to/pdf.pdf\"): print(\"page start\", page.page_num) for item in page: print(\" >\", item) print(\"page end\", page.page_num) Why Another Fork? PDFMiner was designed to run in python 2.7>, PDFMiner.six was written to bring cross-version support for python 2 and 3. However, after attempting to build and extend upon PDFMiner.six I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports. Features Functional extraction method based on generators Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) Font-Color extraction Shape fill and stroke color extraction CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Note : We took out the layout-analysis process in this version (there is no more LTTextHorizontal or LTTextVertical). While the mathematics behind the grouping process was sound, the coupling of the layout-analysis process with the parsing and interpretation process produced unfriendly-code. This feature could be brought back by running your own implementation of it on the pdfmajor.interpreter.PageInterpreter class, but at the current time is not supported. How to Install Source Install Python 3.6.4 or newer. clone this repo git clone https://github.com/asosnovsky/pdfmajor * install repo python setup.py install Pypi Install Python 3.6.4 or newer. install repo pip install pdfmajor Terms and Conditions (This is so-called MIT/X License) Copyright (c) 2018-2019 Ariel Sosnovsky Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the \"Software\"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.","title":"Home"},{"location":"#pdfmajor","text":"Latest Release PDF-Major is a fork of PDFMiner.six . It is meant to be a more light-weight implementation that makes fewer assumptions on the data. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon.","title":"PDFMajor"},{"location":"#documentation","text":"See documentation here .","title":"Documentation"},{"location":"#basic-example","text":"from pdfmajor.interpreter import PDFInterpreter for page in PDFInterpreter(\"/path/to/pdf.pdf\"): print(\"page start\", page.page_num) for item in page: print(\" >\", item) print(\"page end\", page.page_num)","title":"Basic Example"},{"location":"#why-another-fork","text":"PDFMiner was designed to run in python 2.7>, PDFMiner.six was written to bring cross-version support for python 2 and 3. However, after attempting to build and extend upon PDFMiner.six I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports.","title":"Why Another Fork?"},{"location":"#features","text":"Functional extraction method based on generators Parse, analyze, and convert PDF documents. PDF-1.7 specification support. (well, almost) Font-Color extraction Shape fill and stroke color extraction CJK languages and vertical writing scripts support. Various font types (Type1, TrueType, Type3, and CID) support. Basic encryption (RC4) support. Note : We took out the layout-analysis process in this version (there is no more LTTexLine truncated
|
||||
+2
-2
@@ -2,12 +2,12 @@
|
||||
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
|
||||
<url>
|
||||
<loc>None</loc>
|
||||
<lastmod>2019-01-11</lastmod>
|
||||
<lastmod>2019-12-08</lastmod>
|
||||
<changefreq>daily</changefreq>
|
||||
</url>
|
||||
<url>
|
||||
<loc>None</loc>
|
||||
<lastmod>2019-01-11</lastmod>
|
||||
<lastmod>2019-12-08</lastmod>
|
||||
<changefreq>daily</changefreq>
|
||||
</url>
|
||||
</urlset>
|
||||
Binary file not shown.
@@ -16,11 +16,11 @@
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
PDF-Major is a fork of `PDFMiner.six`. It is meant to be a more light-weight implementation that makes fewer assumptions on the data. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon.
|
||||
PDF-Major is a **complete re-write** of `PDFMiner.six`. It is meant to be a more light-weight implementation that makes fewer assumptions on the data. The ultimate goal of this project is to provide a simpler, faster and more functional library that both casual and low-level developers could build upon.
|
||||
|
||||
## Documentation
|
||||
|
||||
See documentation [here](https://asosnovsky.github.io/pdfmajor/).
|
||||
See [full API documentation here](https://asosnovsky.github.io/pdfmajor/api/).
|
||||
|
||||
## Basic Example
|
||||
```py
|
||||
@@ -34,9 +34,9 @@ for page in PDFInterpreter("/path/to/pdf.pdf"):
|
||||
|
||||
```
|
||||
|
||||
## Why Another Fork?
|
||||
## Why a re-write?
|
||||
|
||||
`PDFMiner` was designed to run in python 2.7>, `PDFMiner.six` was written to bring cross-version support for python 2 and 3. However, after attempting to build and extend upon `PDFMiner.six` I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports.
|
||||
`PDFMiner` was designed to run in python 2.7, `PDFMiner.six` was written to bring cross-version support for python 2 and 3. However, after attempting to build and extend upon `PDFMiner.six` I found it rather difficult to extend and identify additional details regarding the items encoded in the pdf. This library will attempt to expose as much information as possible to end-users, without having them solely rely on to-xml or to-json exports.
|
||||
|
||||
## Features
|
||||
|
||||
@@ -97,7 +97,7 @@ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
||||
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
|
||||
"""
|
||||
__version__ = (1, 3, 8)
|
||||
__version__ = (1, 3, 11)
|
||||
|
||||
if __name__ == '__main__':
|
||||
print(
|
||||
|
||||
@@ -22,6 +22,7 @@ def convert_file(
|
||||
check_extractable: bool = True,
|
||||
pagenos: Optional[List[int]] = None,
|
||||
dont_export_images: bool = False,
|
||||
ignore_bad_chars: bool = False,
|
||||
debug_level: int = logging.WARNING,
|
||||
out_type: str = 'html',
|
||||
):
|
||||
@@ -45,6 +46,7 @@ def convert_file(
|
||||
password=password,
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
pagenos=pagenos,
|
||||
debug_level=debug_level,
|
||||
)
|
||||
@@ -59,6 +61,7 @@ def convert_file(
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
pagenos=pagenos,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
dont_export_images=dont_export_images,
|
||||
debug_level=debug_level,
|
||||
)
|
||||
@@ -73,6 +76,7 @@ def convert_file(
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
pagenos=pagenos,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
dont_export_images=dont_export_images,
|
||||
debug_level=debug_level,
|
||||
)
|
||||
@@ -87,6 +91,7 @@ def convert_file(
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
pagenos=pagenos,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
dont_export_images=dont_export_images,
|
||||
debug_level=debug_level,
|
||||
)
|
||||
@@ -101,6 +106,7 @@ def convert_file(
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
pagenos=pagenos,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
dont_export_images=dont_export_images,
|
||||
debug_level=debug_level,
|
||||
)
|
||||
|
||||
@@ -16,6 +16,7 @@ def convert_to_html(
|
||||
maxpages: int = 0,
|
||||
password: Optional[str] = None,
|
||||
caching: bool = True,
|
||||
ignore_bad_chars: bool = False,
|
||||
check_extractable: bool = True,
|
||||
pagenos: List[int] = None,
|
||||
debug_level: int = logging.WARNING,
|
||||
@@ -25,6 +26,7 @@ def convert_to_html(
|
||||
password=password,
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
pagenos=pagenos,
|
||||
debug_level=debug_level
|
||||
)
|
||||
|
||||
@@ -28,6 +28,7 @@ def convert_to_json(
|
||||
password: str = Optional[None],
|
||||
caching: bool = True,
|
||||
check_extractable: bool = True,
|
||||
ignore_bad_chars: bool = False,
|
||||
pagenos: Optional[List[int]] = None,
|
||||
debug_level: int = logging.WARNING,
|
||||
):
|
||||
@@ -36,6 +37,7 @@ def convert_to_json(
|
||||
password=password,
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
pagenos=pagenos,
|
||||
debug_level=debug_level
|
||||
)
|
||||
|
||||
@@ -14,6 +14,7 @@ def convert_to_text(
|
||||
password: str = None,
|
||||
caching: bool = True,
|
||||
check_extractable: bool = True,
|
||||
ignore_bad_chars: bool = False,
|
||||
pagenos: List[int] = None,
|
||||
debug_level: int = logging.WARNING,
|
||||
):
|
||||
@@ -22,6 +23,7 @@ def convert_to_text(
|
||||
password=password,
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
pagenos=pagenos,
|
||||
debug_level=debug_level
|
||||
)
|
||||
|
||||
@@ -45,6 +45,7 @@ def convert_to_xml(
|
||||
maxpages: int = 0,
|
||||
password: str = None,
|
||||
caching: bool = True,
|
||||
ignore_bad_chars: bool = False,
|
||||
check_extractable: bool = True,
|
||||
pagenos: List[int] = None,
|
||||
debug_level: int = logging.WARNING,
|
||||
@@ -54,6 +55,7 @@ def convert_to_xml(
|
||||
password=password,
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
pagenos=pagenos,
|
||||
debug_level=debug_level
|
||||
)
|
||||
|
||||
@@ -28,6 +28,7 @@ def convert_to_yaml(
|
||||
password: str = None,
|
||||
caching: bool = True,
|
||||
check_extractable: bool = True,
|
||||
ignore_bad_chars: bool = False,
|
||||
pagenos: List[int] = None,
|
||||
debug_level: int = logging.WARNING,
|
||||
):
|
||||
@@ -36,6 +37,7 @@ def convert_to_yaml(
|
||||
password=password,
|
||||
caching=caching,
|
||||
check_extractable=check_extractable,
|
||||
ignore_bad_chars=ignore_bad_chars,
|
||||
pagenos=pagenos,
|
||||
debug_level=debug_level
|
||||
)
|
||||
|
||||
@@ -0,0 +1,2 @@
|
||||
import pdfmajor.parser.exceptions as parser
|
||||
import pdfmajor.interpreter.exceptions as interpreter
|
||||
@@ -5,9 +5,8 @@ from .commands import PDFStateStack
|
||||
from .commands import process_command_stream, prep_state
|
||||
|
||||
class PageInterpreter:
|
||||
class PDFInterpreterError(Exception): pass
|
||||
|
||||
def __init__(self, page: PDFPage, page_num: int, font_cache: dict = {}):
|
||||
def __init__(self, page: PDFPage, page_num: int, font_cache: dict = None, ignore_bad_chars = False):
|
||||
(x0, y0, x1, y1) = page.mediabox
|
||||
if page.rotate == 90:
|
||||
ctm = [0, -1, 1, 0, -y0, x1]
|
||||
@@ -19,7 +18,7 @@ class PageInterpreter:
|
||||
ctm = [1, 0, 0, 1, -x0, -y0]
|
||||
|
||||
# Locals
|
||||
self.font_cache = font_cache
|
||||
self.font_cache = font_cache if font_cache is not None else {}
|
||||
self.page = page
|
||||
self.page_num = page_num
|
||||
self.height = y1-y0
|
||||
@@ -30,7 +29,8 @@ class PageInterpreter:
|
||||
PDFStateStack(),
|
||||
ctm=ctm,
|
||||
resources=page.resources,
|
||||
font_cache=self.font_cache
|
||||
font_cache=self.font_cache,
|
||||
ignore_bad_chars=ignore_bad_chars
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -1,7 +1,5 @@
|
||||
from typing import List
|
||||
|
||||
from tqdm import tqdm
|
||||
|
||||
from ..parser.PDFPage import PDFPage
|
||||
from ..utils import set_log_level, get_logger, logging
|
||||
from .commands.state import PDFStateStack, PDFColorSpace, PREDEFINED_COLORSPACE
|
||||
@@ -25,6 +23,7 @@ class PDFInterpreter:
|
||||
password: str = None,
|
||||
pagenos: List[int] = None,
|
||||
preload: bool = False,
|
||||
ignore_bad_chars: bool = False,
|
||||
debug_level: int = logging.WARNING,
|
||||
):
|
||||
self.input_file_path = input_file_path
|
||||
@@ -33,6 +32,7 @@ class PDFInterpreter:
|
||||
self.check_extractable = check_extractable
|
||||
self.password = password
|
||||
self.pagenos = pagenos
|
||||
self.ignore_bad_chars = ignore_bad_chars
|
||||
self.debug_level = debug_level
|
||||
self.__pages = []
|
||||
if preload:
|
||||
@@ -53,8 +53,8 @@ class PDFInterpreter:
|
||||
caching=self.caching,
|
||||
check_extractable=self.check_extractable
|
||||
)
|
||||
for page_num, page in tqdm(enumerate(pages), desc="Reading pages...", disable=self.debug_level > logging.INFO):
|
||||
self.__pages.append(PageInterpreter(page, page_num, font_cache))
|
||||
for page_num, page in enumerate(pages):
|
||||
self.__pages.append(PageInterpreter(page, page_num, font_cache, ignore_bad_chars=self.ignore_bad_chars))
|
||||
yield self.__pages[-1]
|
||||
log.info(f"Done Reading {len(self.__pages)} pages.")
|
||||
set_log_level(logging.WARNING)
|
||||
@@ -64,7 +64,7 @@ class PDFInterpreter:
|
||||
def __iter__(self):
|
||||
if len(self.__pages) > 0:
|
||||
set_log_level(self.debug_level)
|
||||
for page in tqdm(self.__pages, desc="Reading pages from store...", disable=self.debug_level > logging.INFO):
|
||||
for page in self.__pages:
|
||||
yield page
|
||||
set_log_level(logging.WARNING)
|
||||
else:
|
||||
|
||||
@@ -7,17 +7,18 @@ from pdfmajor.parser.constants import LITERAL_FORM, LITERAL_IMAGE
|
||||
from .state import PDFStateStack, PDFColorSpace
|
||||
from .state.Curves import CurveMethod, CurvePath, CurvePoint
|
||||
|
||||
class PDFCommandsInvalidOperation(Exception): pass
|
||||
class PDFCommandsRepeatedCommand(Exception): pass
|
||||
|
||||
class PDFCommands:
|
||||
commands = {}
|
||||
class InvalidOperation(Exception): pass
|
||||
class RepeatedCommand(Exception): pass
|
||||
|
||||
@classmethod
|
||||
def __add(cls, cmd_name: str, cmd: callable):
|
||||
if not (cmd_name in cls.commands.keys()):
|
||||
cls.commands[cmd_name] = cmd
|
||||
return cmd
|
||||
raise cls.RepeatedCommand(cmd_name)
|
||||
raise PDFCommandsRepeatedCommand(cmd_name)
|
||||
|
||||
@classmethod
|
||||
def add(cls, *cmd_names: List[str]):
|
||||
|
||||
@@ -71,9 +71,10 @@ def process_command_stream(streams: List[PDFStream], font_cache: dict = None, st
|
||||
yield complete_item
|
||||
state.complete_layout_items = []
|
||||
|
||||
def prep_state(state: PDFStateStack, ctm: tuple, resources: dict, font_cache: dict) -> PDFStateStack:
|
||||
def prep_state(state: PDFStateStack, ctm: tuple, resources: dict, font_cache: dict, ignore_bad_chars: bool = False) -> PDFStateStack:
|
||||
state.t_matrix = ctm
|
||||
state.resources = resources
|
||||
state.text.ignore_bad_chars = ignore_bad_chars
|
||||
|
||||
# set some global states.
|
||||
state.graphics.ncolspace = state.graphics.scolspace = None
|
||||
|
||||
@@ -3,7 +3,7 @@ from pdfmajor.parser.PSStackParser import literal_name
|
||||
from pdfmajor.parser.PDFStream import PDFStream, list_value, dict_value
|
||||
from pdfmajor.parser.constants import LITERAL_FORM, LITERAL_IMAGE
|
||||
|
||||
from .PDFCommands import PDFCommands
|
||||
from .PDFCommands import PDFCommands, PDFCommandsInvalidOperation, PDFCommandsRepeatedCommand
|
||||
from .state import PDFStateStack, PDFGraphicState, LTTextBlock
|
||||
from .state.Curves import CurveMethod, CurvePath, CurvePoint
|
||||
# from .state.PDFItem import PDFImage, PDFShape, PDFText, PDFXObject
|
||||
@@ -253,7 +253,7 @@ def set_stroke_colorspace(stack: PDFStateStack, name: str) -> PDFStateStack:
|
||||
stack.graphics.scolspace = stack.colorspace_map[literal_name(name)]
|
||||
return stack
|
||||
except KeyError:
|
||||
raise PDFCommands.InvalidOperation('Undefined ColorSpace: %r' % name)
|
||||
raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
|
||||
|
||||
# setcolorspace-non-strokine
|
||||
@PDFCommands.add('cs')
|
||||
@@ -262,7 +262,7 @@ def set_nonstroke_colorspace(stack: PDFStateStack, name: str) -> PDFStateStack:
|
||||
stack.graphics.ncolspace = stack.colorspace_map[literal_name(name)]
|
||||
return stack
|
||||
except KeyError:
|
||||
raise PDFCommands.InvalidOperation('Undefined ColorSpace: %r' % name)
|
||||
raise PDFCommandsInvalidOperation('Undefined ColorSpace: %r' % name)
|
||||
|
||||
# setgray-stroking
|
||||
@PDFCommands.add('G')
|
||||
@@ -326,7 +326,7 @@ def set_nonstroke_cmyk(stack: PDFStateStack, c, m, y, k) -> PDFStateStack:
|
||||
@PDFCommands.add('SCN','SC')
|
||||
def set_stroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
||||
if stack.graphics.scolspace is None:
|
||||
raise PDFCommands.InvalidOperation('No colorspace specified!')
|
||||
raise PDFCommandsInvalidOperation('No colorspace specified!')
|
||||
components = stack.pop(stack.graphics.scolspace.ncomponents)
|
||||
stack.graphics.set_stroke_color(
|
||||
stack.graphics.scolspace,
|
||||
@@ -337,7 +337,7 @@ def set_stroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
||||
@PDFCommands.add('scn','sc')
|
||||
def set_nonstroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
|
||||
if stack.graphics.ncolspace is None:
|
||||
raise PDFCommands.InvalidOperation('No colorspace specified!')
|
||||
raise PDFCommandsInvalidOperation('No colorspace specified!')
|
||||
components = stack.pop(stack.graphics.ncolspace.ncomponents)
|
||||
stack.graphics.set_nostroke_color(
|
||||
stack.graphics.ncolspace,
|
||||
@@ -353,7 +353,7 @@ def begin_text(stack: PDFStateStack) -> PDFStateStack:
|
||||
if stack.current_textblock is None:
|
||||
stack.current_textblock = LTTextBlock()
|
||||
else:
|
||||
raise PDFCommands.InvalidOperation("Last TextBlock did not clear")
|
||||
raise PDFCommandsInvalidOperation("Last TextBlock did not clear")
|
||||
return stack
|
||||
|
||||
@PDFCommands.add('ET')
|
||||
@@ -394,7 +394,7 @@ def set_font(stack: PDFStateStack, fontid, fontsize) -> PDFStateStack:
|
||||
stack.text.font = stack.fontmap[literal_name(fontid)]
|
||||
return stack
|
||||
except KeyError:
|
||||
raise PDFCommands.InvalidOperation('Undefined Font id: %r' % fontid)
|
||||
raise PDFCommandsInvalidOperation('Undefined Font id: %r' % fontid)
|
||||
|
||||
# setrendering
|
||||
@PDFCommands.add('Tr')
|
||||
@@ -444,9 +444,9 @@ def nextline(stack: PDFStateStack) -> PDFStateStack:
|
||||
@PDFCommands.add('TJ')
|
||||
def add_char_blocks(stack: PDFStateStack, seq: bytearray) -> PDFStateStack:
|
||||
if stack.text.font is None:
|
||||
raise PDFCommands.InvalidOperation("No Font Specified")
|
||||
raise PDFCommandsInvalidOperation("No Font Specified")
|
||||
if stack.current_textblock is None:
|
||||
raise PDFCommands.InvalidOperation("No TextBlock initilized")
|
||||
raise PDFCommandsInvalidOperation("No TextBlock initilized")
|
||||
stack.current_textblock.add_char_block(
|
||||
seq,
|
||||
stack.t_matrix,
|
||||
@@ -487,7 +487,7 @@ def insert_xobject(stack: PDFStateStack, xobjid) -> PDFStateStack:
|
||||
try:
|
||||
xobj = PDFStream.validated_stream(stack.xobjmap[xobjid])
|
||||
except KeyError:
|
||||
raise PDFCommands.InvalidOperation('Undefined xobject id: %r' % xobjid)
|
||||
raise PDFCommandsInvalidOperation('Undefined xobject id: %r' % xobjid)
|
||||
# log.info('Processing xobj: %r', xobj)
|
||||
subtype = xobj.get('Subtype')
|
||||
if subtype is LITERAL_FORM and 'BBox' in xobj:
|
||||
|
||||
@@ -2,7 +2,6 @@ from .PDFColor import PDFColor, PDFColorSpace
|
||||
from .PDFColorSpace import PREDEFINED_COLORSPACE
|
||||
|
||||
class PDFGraphicState(object):
|
||||
class InvalidOperation(Exception): pass
|
||||
|
||||
def __init__(self):
|
||||
self.linewidth = 0
|
||||
|
||||
@@ -58,7 +58,7 @@ class PDFText(PDFItem):
|
||||
if needcharspace:
|
||||
textstate.linematrix[idx] += textstate.charspace
|
||||
|
||||
text = textstate.font.to_unichr(cid)
|
||||
text = textstate.to_unichr(cid)
|
||||
assert isinstance(text, str), str(type(text))
|
||||
|
||||
matrix = translate_matrix(textstate.matrix, textstate.linematrix)
|
||||
|
||||
@@ -42,7 +42,7 @@ class TextDecoder:
|
||||
if needcharspace:
|
||||
textstate.linematrix[idx] += textstate.charspace
|
||||
|
||||
text = textstate.font.to_unichr(cid)
|
||||
text = textstate.to_unichr(cid)
|
||||
assert isinstance(text, str), str(type(text))
|
||||
|
||||
matrix = translate_matrix(textstate.matrix, textstate.linematrix)
|
||||
|
||||
@@ -10,10 +10,10 @@ from pdfmajor.parser.PDFStream import resolve1
|
||||
from pdfmajor.parser.PDFStream import int_value
|
||||
from pdfmajor.parser.PDFStream import num_value
|
||||
from pdfmajor.parser.PDFStream import list_value
|
||||
from pdfmajor.parser.PDFStream import PDFException
|
||||
from pdfmajor.parser.PDFStream import PDFStream
|
||||
from pdfmajor.parser.cmapdb import FileUnicodeMap
|
||||
from pdfmajor.parser.cmapdb import CMapParser
|
||||
from .execptions import PDFFontError, PDFUnicodeNotDefined
|
||||
|
||||
## Literals
|
||||
##
|
||||
@@ -22,8 +22,6 @@ LITERAL_TYPE1C = LIT('Type1C')
|
||||
|
||||
|
||||
class PDFFont(object):
|
||||
class PDFFontError(PDFException): pass
|
||||
class PDFUnicodeNotDefined(PDFFontError): pass
|
||||
|
||||
def __init__(self, descriptor, widths, default_width=None):
|
||||
self.descriptor = descriptor
|
||||
@@ -77,7 +75,7 @@ class PDFFont(object):
|
||||
except KeyError:
|
||||
try:
|
||||
return self.widths[self.to_unichr(cid)] * self.hscale
|
||||
except (KeyError, self.PDFUnicodeNotDefined):
|
||||
except (KeyError, PDFUnicodeNotDefined):
|
||||
return self.default_width * self.hscale
|
||||
|
||||
def char_disp(self, cid):
|
||||
@@ -137,4 +135,4 @@ class PDFSimpleFont(PDFFont):
|
||||
try:
|
||||
return self.cid2unicode[cid]
|
||||
except KeyError:
|
||||
raise self.PDFUnicodeNotDefined(None, cid)
|
||||
raise PDFUnicodeNotDefined(None, cid)
|
||||
@@ -4,6 +4,7 @@ from pdfmajor.parser.PDFStream import list_value
|
||||
from pdfmajor.parser.PDFStream import dict_value
|
||||
from pdfmajor.parser.PDFStream import resolve1
|
||||
from pdfmajor.parser.constants import LITERAL_FONT
|
||||
from .execptions import PDFFontError
|
||||
|
||||
from .fonts import PDFType1Font, PDFTrueTypeFont, PDFType3Font, PDFCIDFont, PDFFont
|
||||
|
||||
@@ -16,13 +17,13 @@ def get_font(objid: int, spec: dict, cached_fonts: dict = {}):
|
||||
log.debug('get_font: create: objid=%r, spec=%r', objid, spec)
|
||||
if settings.STRICT:
|
||||
if spec['Type'] is not LITERAL_FONT:
|
||||
raise PDFFont.PDFFontError('Type is not /Font')
|
||||
raise PDFFontError('Type is not /Font')
|
||||
# Create a Font object.
|
||||
if 'Subtype' in spec:
|
||||
subtype = literal_name(spec['Subtype'])
|
||||
else:
|
||||
if settings.STRICT:
|
||||
raise PDFFont.PDFFontError('Font Subtype is not specified.')
|
||||
raise PDFFontError('Font Subtype is not specified.')
|
||||
subtype = 'Type1'
|
||||
if subtype in ('Type1', 'MMType1'):
|
||||
# Type1 Font
|
||||
@@ -47,7 +48,7 @@ def get_font(objid: int, spec: dict, cached_fonts: dict = {}):
|
||||
font = get_font(None, subspec, cached_fonts)
|
||||
else:
|
||||
if settings.STRICT:
|
||||
raise PDFFont.PDFFontError('Invalid Font spec: %r' % spec)
|
||||
raise PDFFontError('Invalid Font spec: %r' % spec)
|
||||
font = PDFType1Font(spec) # this is so wrong!
|
||||
if objid:
|
||||
cached_fonts[objid] = font
|
||||
|
||||
@@ -0,0 +1,4 @@
|
||||
from pdfmajor.parser.PDFStream import PDFException
|
||||
|
||||
class PDFFontError(PDFException): pass
|
||||
class PDFUnicodeNotDefined(PDFFontError): pass
|
||||
@@ -15,6 +15,7 @@ from .PDFFont import PDFFont, PDFSimpleFont
|
||||
from .util import FontMetricsDB, get_widths, get_widths2
|
||||
from .Type1FontHeaderParser import Type1FontHeaderParser
|
||||
from .TrueTypeFont import TrueTypeFont
|
||||
from .execptions import PDFFontError, PDFUnicodeNotDefined
|
||||
|
||||
# PDFType1Font
|
||||
class PDFType1Font(PDFSimpleFont):
|
||||
@@ -24,7 +25,7 @@ class PDFType1Font(PDFSimpleFont):
|
||||
self.basefont = literal_name(spec['BaseFont'])
|
||||
except KeyError:
|
||||
if settings.STRICT:
|
||||
raise self.PDFFontError('BaseFont is missing')
|
||||
raise PDFFontError('BaseFont is missing')
|
||||
self.basefont = 'unknown'
|
||||
try:
|
||||
(descriptor, widths) = FontMetricsDB.get_metrics(self.basefont)
|
||||
@@ -86,7 +87,7 @@ class PDFCIDFont(PDFFont):
|
||||
self.basefont = literal_name(spec['BaseFont'])
|
||||
except KeyError:
|
||||
if strict:
|
||||
raise self.PDFFontError('BaseFont is missing')
|
||||
raise PDFFontError('BaseFont is missing')
|
||||
self.basefont = 'unknown'
|
||||
self.cidsysteminfo = dict_value(spec.get('CIDSystemInfo', {}))
|
||||
self.cidcoding = '%s-%s' % (resolve1(self.cidsysteminfo.get('Registry', b'unknown')).decode("latin1"),
|
||||
@@ -95,19 +96,19 @@ class PDFCIDFont(PDFFont):
|
||||
name = literal_name(spec['Encoding'])
|
||||
except KeyError:
|
||||
if strict:
|
||||
raise self.PDFFontError('Encoding is unspecified')
|
||||
raise PDFFontError('Encoding is unspecified')
|
||||
name = 'unknown'
|
||||
try:
|
||||
self.cmap = CMapDB.get_cmap(name)
|
||||
except CMapDB.CMapNotFound as e:
|
||||
if strict:
|
||||
raise self.PDFFontError(e)
|
||||
raise PDFFontError(e)
|
||||
self.cmap = CMap()
|
||||
try:
|
||||
descriptor = dict_value(spec['FontDescriptor'])
|
||||
except KeyError:
|
||||
if strict:
|
||||
raise self.PDFFontError('FontDescriptor is missing')
|
||||
raise PDFFontError('FontDescriptor is missing')
|
||||
descriptor = {}
|
||||
ttf = None
|
||||
if 'FontFile2' in descriptor:
|
||||
@@ -171,4 +172,4 @@ class PDFCIDFont(PDFFont):
|
||||
raise KeyError(cid)
|
||||
return self.unicode_map.get_unichr(cid)
|
||||
except KeyError:
|
||||
raise self.PDFUnicodeNotDefined(self.cidcoding, cid)
|
||||
raise PDFUnicodeNotDefined(self.cidcoding, cid)
|
||||
@@ -1,5 +1,6 @@
|
||||
from .PDFFont import PDFFont, get_font
|
||||
from pdfmajor.utils import MATRIX_IDENTITY
|
||||
from .PDFFont import PDFFont, get_font
|
||||
from .PDFFont.execptions import PDFUnicodeNotDefined, PDFFontError
|
||||
|
||||
## PDFTextState
|
||||
##
|
||||
@@ -16,14 +17,27 @@ class PDFTextState(object):
|
||||
self.rise: int = 0
|
||||
self.matrix = MATRIX_IDENTITY
|
||||
self.linematrix = [0, 0]
|
||||
self.ignore_bad_chars = False
|
||||
|
||||
def __repr__(self):
|
||||
return ('<PDFTextState: font=%r, fontsize=%r, charspace=%r, wordspace=%r, '
|
||||
' scaling=%r, leading=%r, render=%r, rise=%r, '
|
||||
' matrix=%r, linematrix=%r>' %
|
||||
' matrix=%r, linematrix=%r ignore_bad_chars=%r>' %
|
||||
(self.font, self.fontsize, self.charspace, self.wordspace,
|
||||
self.scaling, self.leading, self.render, self.rise,
|
||||
self.matrix, self.linematrix))
|
||||
self.matrix, self.linematrix, self.ignore_bad_chars))
|
||||
|
||||
def to_unichr(self, cid: int) -> str:
|
||||
if self.font is None:
|
||||
raise PDFFontError("Missing font")
|
||||
try:
|
||||
return self.font.to_unichr(cid)
|
||||
except PDFUnicodeNotDefined as e:
|
||||
if self.ignore_bad_chars:
|
||||
return ""
|
||||
else:
|
||||
raise e
|
||||
|
||||
|
||||
def copy(self):
|
||||
obj = self.__class__()
|
||||
@@ -37,6 +51,7 @@ class PDFTextState(object):
|
||||
obj.rise = self.rise
|
||||
obj.matrix = self.matrix
|
||||
obj.linematrix = self.linematrix
|
||||
obj.ignore_bad_chars = self.ignore_bad_chars
|
||||
return obj
|
||||
|
||||
def reset_matrices(self):
|
||||
|
||||
@@ -33,7 +33,7 @@ def __render_string_along(idx: int, seq: bytearray,
|
||||
if needcharspace:
|
||||
textstate.linematrix[idx] += textstate.charspace
|
||||
|
||||
text = textstate.font.to_unichr(cid)
|
||||
text = textstate.to_unichr(cid)
|
||||
assert isinstance(text, str), str(type(text))
|
||||
|
||||
matrix = translate_matrix(textstate.matrix, textstate.linematrix)
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
from .commands import CommandProcessorError
|
||||
from .commands.PDFCommands import PDFCommandsRepeatedCommand, PDFCommandsInvalidOperation
|
||||
from .commands.state.PDFTextState.PDFFont.execptions import *
|
||||
@@ -0,0 +1,5 @@
|
||||
from .cmapdb import CMapError
|
||||
from .PDFStream.exceptions import *
|
||||
from .PDFDocument.exceptions import *
|
||||
from .PSStackParser.exceptions import *
|
||||
from .PDFParser import PDFSyntaxError
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 14 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 576 KiB |
Binary file not shown.
Binary file not shown.
@@ -10,17 +10,17 @@ import sys
|
||||
with open('README.md') as readme_file:
|
||||
SETUP = {
|
||||
"name": "pdfmajor",
|
||||
"version": "1.3.8",
|
||||
"version": "1.3.12",
|
||||
"packages": find_packages(include=['pdfmajor*']),
|
||||
"install_requires": [
|
||||
'pycryptodome==3.8.2',
|
||||
'chardet==3.0.4',
|
||||
'Pillow==6.0.0'
|
||||
'Pillow>=6.2.0'
|
||||
],
|
||||
'extras_require': {
|
||||
'dev': [
|
||||
'tqdm==4.32.1',
|
||||
'nose==1.3.7'
|
||||
'mkdocs==1.0.4'
|
||||
]
|
||||
},
|
||||
"description": 'PDF parser',
|
||||
|
||||
Binary file not shown.
Executable
BIN
Binary file not shown.
@@ -0,0 +1,23 @@
|
||||
from pathlib import Path
|
||||
from unittest import TestCase, main
|
||||
|
||||
from pdfmajor.interpreter import PDFInterpreter, exceptions
|
||||
|
||||
CURRENT_FOLDER = Path("./")
|
||||
|
||||
class BadUnicode(TestCase):
|
||||
def test_ensure_failure(self):
|
||||
pdf = PDFInterpreter(CURRENT_FOLDER / "tests" / "samples" / "pdf" / "bad-unicode.pdf", ignore_bad_chars=False)
|
||||
pages = list(pdf)
|
||||
with self.assertRaises(exceptions.PDFUnicodeNotDefined):
|
||||
list(pages[2])
|
||||
|
||||
def test_ensure_no_failure(self):
|
||||
pdf = PDFInterpreter(CURRENT_FOLDER / "tests" / "samples" / "pdf" / "bad-unicode.pdf", ignore_bad_chars=True)
|
||||
pages = list(pdf)
|
||||
list(pages[2])
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# Run Tests
|
||||
main()
|
||||
@@ -14,7 +14,7 @@ NUM_LOOPS = 10
|
||||
|
||||
def count_elms(file_path: str):
|
||||
count = 0
|
||||
for page in PDFInterpreter(file_path):
|
||||
for page in PDFInterpreter(file_path, ignore_bad_chars=True):
|
||||
for item in page:
|
||||
if isinstance(item, LTContainer):
|
||||
count += len([*item])
|
||||
|
||||
@@ -42,6 +42,7 @@ class ConversionTest(TestCase):
|
||||
input_file=input_file_path,
|
||||
output_file=output_file_path,
|
||||
out_type=ext,
|
||||
ignore_bad_chars=True,
|
||||
debug_level=logging.WARN,
|
||||
)
|
||||
if ext == 'xml':
|
||||
|
||||
@@ -16,7 +16,7 @@ class TestInterpreter(TestCase):
|
||||
for file_name in FILES:
|
||||
self.subTest(file_name=file_name)
|
||||
file_path = os.path.join(INPUT_FOLDER, file_name)
|
||||
for page in PDFInterpreter(file_path, debug_level=logging.ERROR):
|
||||
for page in PDFInterpreter(file_path, debug_level=logging.ERROR, ignore_bad_chars=True):
|
||||
self.assertTrue( isinstance(page, PageInterpreter) )
|
||||
for item in page:
|
||||
self.assertTrue( isinstance(item, LTItem) )
|
||||
|
||||
Reference in new issue
Block a user