Author SHA1 Message Date
ari 7e24c64b5b Centralized all exceptions 2019-12-19 22:04:01 -05:00
ari cdcd2eabe2 ensured tests are passing 2019-12-19 21:58:44 -05:00
ari fdd2fbd85a removed old exception files 2019-12-19 20:18:49 -05:00
ari 087012dd81 all errors caught in one location 2019-12-19 20:08:06 -05:00
ari 630b3b2418 removed unused cmd_record 2019-12-12 21:45:22 -05:00
ari 441abc3f55 version bump 2019-12-11 22:18:51 -05:00
ari 152d3aaf55 v1.3.12 2019-12-11 22:16:28 -05:00
ari 36a9371657 generated docs 2019-12-08 14:45:28 -05:00
ari a29d465ea4 added support for ignore bad char flag
- updated unit tests to include
- using the textstate.to_unichr abstraction
2019-12-08 14:44:46 -05:00
ari 841576d9b8 exposed exceptions to top module
updated dependencies
2019-12-07 23:15:55 -05:00
ari bfc0b6ba34 added venv 2019-12-07 23:15:12 -05:00
ari 336f5f1fba propograted exceptions 2019-12-07 22:58:13 -05:00
ari 1b1db13b5b updated deps
- upgraded to Pillow 6.2.0 (passes tests)
- removed unnecessary nose dep
2019-12-07 22:57:57 -05:00
ari 3f561f3488 - removed none-develop dependency on tqdm
- ensured all test pdfs are properly pushed
2019-08-18 18:00:50 -04:00
ari 989de3122e corrected gitignore to not ignore lorem-v5.pdf 2019-08-18 17:59:14 -04:00
ari 20be0aa49e removed dependency on tqdm 2019-08-18 17:55:08 -04:00
ari d37b56a685 Merge branch 'master' of github.com:asosnovsky/pdfmajor 2019-06-10 16:28:23 -04:00
ari 9e923de7ec - added better mypy support
- updated most unit-test to use the unitttest module
- added a single unit-test run file
2019-06-10 16:26:52 -04:00
Ari Sosnovsky 2c9593ac21 Update README.md 2019-04-01 17:37:13 -04:00
Ari Sosnovsky 057cc0cf28 Update README.md 2019-04-01 17:36:36 -04:00
Ari Sosnovsky 82b47f1b19 Update README.md 2019-04-01 17:35:24 -04:00
ari 290de97cb5 - fixed invisible color bug 2019-01-26 23:08:57 -05:00
ari b32aef7fda - fixed the curve ignoring of the color error 2019-01-24 21:38:47 -05:00
76 changed files with 720 additions and 442 deletions

No files matched your search

+5 -2
View File
@@ -10,5 +10,8 @@ tests/*.txt
.idea/
.vscode
tests/samples/output
samples
**__pycache**
./samples
**__pycache**\
.mypy_cache
.ipynb_checkpoints
venv
+1 -1
View File
@@ -1 +1 @@
v1.3.6
v1.3.13
+4 -4
View File
@@ -11,11 +11,11 @@
</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
@@ -29,9 +29,9 @@ 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
+13 -7
View File
@@ -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
+1
View File
@@ -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
+1
View File
@@ -140,6 +140,7 @@ for page in PDFInterpreter(&quot;/path/to/pdf.pdf&quot;):
<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
View File
@@ -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
View File
@@ -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
View File
@@ -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.
+5 -5
View File
@@ -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, 6)
__version__ = (1, 3, 13)
if __name__ == '__main__':
print(
+14 -7
View File
@@ -2,7 +2,7 @@ import io
import os
import re
from typing import List
from typing import List, Optional
from .html import convert_to_html
from .xml import convert_to_xml
@@ -10,18 +10,20 @@ from .json import convert_to_json
from .text import convert_to_text
from .yaml import convert_to_yaml
from ..utils import logging
from ..execptions import ConverterException
def convert_file(
input_file: str,
output_file: str = None,
image_folder_path: str = None,
output_file: Optional[str] = None,
image_folder_path: Optional[str] = None,
codec: str = 'utf-8',
maxpages: int = 0,
password: str = None,
password: Optional[str] = None,
caching: bool = True,
check_extractable: bool = True,
pagenos: List[int] = None,
pagenos: Optional[List[int]] = None,
dont_export_images: bool = False,
ignore_bad_chars: bool = False,
debug_level: int = logging.WARNING,
out_type: str = 'html',
):
@@ -33,7 +35,7 @@ def convert_file(
)
)
if re.search(re.escape(out_type) + r'$', output_file ) is None:
raise Exception("Please make sure that the file name and output type match!")
raise ConverterException("Please make sure that the file name and output type match!")
if out_type == 'html':
return convert_to_html(
input_file_path=input_file,
@@ -45,6 +47,7 @@ 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 +62,7 @@ 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 +77,7 @@ 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 +92,7 @@ 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,
)
@@ -101,7 +107,8 @@ 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,
)
else: raise Exception("Please specify out_type as 'html' or 'xml' or 'json' or 'text' or 'yaml'")
else: raise ConverterException("Please specify out_type as 'html' or 'xml' or 'json' or 'text' or 'yaml'")
+5 -3
View File
@@ -1,4 +1,4 @@
from typing import List
from typing import List, Optional
from .writers.html import HTMLMaker
from ..interpreter import PDFInterpreter, PageInterpreter, logging
from ..interpreter import LTImage, LTTextBlock, LTCharBlock, LTChar, LTCurve, LTXObject
@@ -10,12 +10,13 @@ INF = (1<<31) - 1
def convert_to_html(
input_file_path: str,
output_file_path: str,
image_folder_path: str = None,
image_folder_path: Optional[str] = None,
dont_export_images: bool = False,
codec: str = 'utf-8',
maxpages: int = 0,
password: str = None,
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
)
+6 -4
View File
@@ -1,4 +1,4 @@
from typing import List
from typing import List, Optional
from .writers.json import JSONMaker, JSONMakerObject, JSONMakerArray
from ..interpreter import PDFInterpreter, PageInterpreter, logging
@@ -21,14 +21,15 @@ def normalize_color_values(values: list):
def convert_to_json(
input_file_path: str,
output_file_path: str,
image_folder_path: str = None,
image_folder_path: Optional[str] = None,
dont_export_images: bool = False,
codec: str = 'utf-8',
maxpages: int = 0,
password: str = None,
password: str = Optional[None],
caching: bool = True,
check_extractable: bool = True,
pagenos: List[int] = None,
ignore_bad_chars: bool = False,
pagenos: Optional[List[int]] = None,
debug_level: int = logging.WARNING,
):
intepreter = PDFInterpreter(input_file_path,
@@ -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
)
+2
View File
@@ -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
)
+8 -6
View File
@@ -1,12 +1,14 @@
from typing import Optional
from io import TextIOWrapper
from contextlib import contextmanager
from pdfmajor.execptions import FileAccessException
class HTMLMaker:
class AccessError(Exception): pass
def __init__(self, file_path: str, codec: str = 'utf-8'):
self.file_path = file_path
self.codec = codec
self.outfile: TextIOWrapper = None
self.outfile: Optional[TextIOWrapper] = None
def __enter__(self):
self.outfile = open(self.file_path, 'wb')
@@ -22,7 +24,7 @@ class HTMLMaker:
text = text.encode(self.codec)
self.outfile.write(text)
else:
raise self.AccessError("Attempting to write to file without an open connection")
raise FileAccessException("Attempting to write to file without an open connection")
def write(self, text: str, lineend: str = '\n', deep_space: str = ' '):
text = deep_space*self.__levels_deep + text + lineend
@@ -42,18 +44,18 @@ class HTMLMaker:
f'{name}: {value}'
for name, value in css.items()
])
attrs = " ".join([
attrs_str = " ".join([
f'{name}="{value}"'
for name, value in attrs.items()
])
if not singleton:
self.write(f"<{tag_name} {attrs}>", lineend=lineend)
self.write(f"<{tag_name} {attrs_str}>", lineend=lineend)
self.__levels_deep += 1
yield
self.__levels_deep -= 1
self.write(f"</{tag_name}>", deep_space=deep_space, lineend='\n' if not nolineend else '')
else:
self.write(f"<{tag_name} {attrs} />", lineend=lineend, deep_space=deep_space)
self.write(f"<{tag_name} {attrs_str} />", lineend=lineend, deep_space=deep_space)
yield
def singleton(self, tag_name: str, attrs: dict = None, css: dict = None, singleton: bool = True):
+5 -6
View File
@@ -1,6 +1,8 @@
from typing import Set
from json import dumps as json_dump
from io import TextIOWrapper
from contextlib import contextmanager
from pdfmajor.execptions import FileAccessException
@contextmanager
def JSONMaker(file_path: str, codec: str = 'utf-8'):
@@ -8,14 +10,12 @@ def JSONMaker(file_path: str, codec: str = 'utf-8'):
with JSONMakerObject(outf, codec=codec) as obj:
yield obj
class JSONMakerObject:
class AccessError(Exception): pass
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = 0):
self.outfile: TextIOWrapper = outfile
self.codec = codec
self.levels_deep = levels_deep
self.keys = set()
self.keys: Set[str] = set()
def __enter__(self):
self.write_raw('{')
@@ -32,7 +32,7 @@ class JSONMakerObject:
text = text.encode(self.codec)
self.outfile.write(text)
else:
raise self.AccessError("Attempting to write to file without an open connection")
raise FileAccessException("Attempting to write to file without an open connection")
def write(self, text: str, deep_space: str = ' ', prefix:str = ''):
text = prefix + (deep_space*self.levels_deep) + text
@@ -71,7 +71,6 @@ class JSONMakerObject:
class JSONMakerArray:
class AccessError(Exception): pass
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = 0):
self.outfile: TextIOWrapper = outfile
self.codec = codec
@@ -93,7 +92,7 @@ class JSONMakerArray:
text = text.encode(self.codec)
self.outfile.write(text)
else:
raise self.AccessError("Attempting to write to file without an open connection")
raise FileAccessException("Attempting to write to file without an open connection")
def write(self, text: str, deep_space: str = ' ', prefix:str = ''):
text = prefix + (deep_space*self.levels_deep) + text
+2 -2
View File
@@ -1,8 +1,8 @@
from io import TextIOWrapper
from contextlib import contextmanager
from pdfmajor.execptions import FileAccessException
class XMLMaker:
class AccessError(Exception): pass
def __init__(self, file_path: str, codec: str = 'utf-8'):
self.file_path = file_path
self.codec = codec
@@ -25,7 +25,7 @@ class XMLMaker:
text = text.encode(self.codec)
self.outfile.write(text)
else:
raise self.AccessError("Attempting to write to file without an open connection")
raise FileAccessException("Attempting to write to file without an open connection")
def write(self, text: str, lineend: str = '\n', deep_space: str = ' '):
text = deep_space*self.__levels_deep + text + lineend
+2 -2
View File
@@ -1,6 +1,7 @@
from json import dumps as json_dump
from io import TextIOWrapper
from contextlib import contextmanager
from pdfmajor.execptions import FileAccessException
@contextmanager
def YAMLMaker(file_path: str, codec: str = 'utf-8'):
@@ -9,7 +10,6 @@ def YAMLMaker(file_path: str, codec: str = 'utf-8'):
yield obj
class YAMLMakerWriter:
class AccessError(Exception): pass
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = -1):
self.outfile: TextIOWrapper = outfile
self.codec = codec
@@ -30,7 +30,7 @@ class YAMLMakerWriter:
text = text.encode(self.codec)
self.outfile.write(text)
else:
raise self.AccessError("Attempting to write to file without an open connection")
raise FileAccessException("Attempting to write to file without an open connection")
def _write(self, text: str, append_deep: bool = True, deep_space: str = ' ', prefix:str = ''):
if not append_deep:
+2
View File
@@ -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
)
+2
View File
@@ -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
)
+105
View File
@@ -0,0 +1,105 @@
class PDFMajorException(Exception):
pass
# Interpreter Errors
class InterpreterError(PDFMajorException):
pass
class EmptyDocumentError(InterpreterError):
pass
class CommandProcessorError(InterpreterError):
pass
class InvalidOperation(CommandProcessorError):
pass
class RepeatedCommand(CommandProcessorError):
pass
class FontError(InterpreterError):
pass
class UnicodeNotDefined(FontError):
pass
class MissingFont(FontError):
pass
# Parser Errors
class ParserError(PDFMajorException):
pass
class PDFNoOutlines(ParserError):
pass
class PDFDestinationNotFound(ParserError):
pass
class PDFNoValidXRef(ParserError):
pass
class CMapNotFound(ParserError):
pass
class PSException(ParserError):
pass
class PDFValueError(ParserError):
pass
class PDFObjectNotFound(ParserError):
pass
class PDFException(ParserError):
pass
class PDFTypeError(PDFException):
pass
class PDFSyntaxError(PDFException):
pass
class PDFTextExtractionNotAllowed(PDFException):
pass
class PSEOF(PSException):
pass
class PSSyntaxError(PSException):
pass
class PSTypeError(PSException):
pass
class PSValueError(PSException):
pass
class CCITTExeception(ParserError):
pass
class EOFB(CCITTExeception):
pass
class InvalidData(CCITTExeception):
pass
class ByteSkip(CCITTExeception):
pass
class PDFTextExtractionNotAllowed(ParserError):
pass
# converter error
class ConverterException(PDFMajorException):
pass
class FileAccessException(ConverterException):
pass
+4 -4
View File
@@ -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
)
+8 -6
View File
@@ -1,6 +1,6 @@
from typing import List
from tqdm import tqdm
from pdfmajor.execptions import EmptyDocumentError
from ..parser.PDFPage import PDFPage
from ..utils import set_log_level, get_logger, logging
@@ -15,7 +15,6 @@ from .PageInterpreter import PageInterpreter
log = get_logger(__name__)
class PDFInterpreter:
class AccessError(Exception): pass
def __init__(self,
input_file_path: str,
@@ -25,6 +24,7 @@ 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 +33,7 @@ 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:
@@ -53,18 +54,19 @@ 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)
if len(self.__pages) == 0:
raise self.AccessError("No pages found in pdf-file")
raise EmptyDocumentError("No pages found in pdf-file")
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:
+3 -3
View File
@@ -1,5 +1,6 @@
from typing import List
from pdfmajor.execptions import RepeatedCommand
from pdfmajor.utils import MATRIX_IDENTITY, mult_matrix
from pdfmajor.parser.PSStackParser import literal_name
from pdfmajor.parser.PDFStream import PDFStream, list_value, dict_value
@@ -7,17 +8,16 @@ from pdfmajor.parser.constants import LITERAL_FORM, LITERAL_IMAGE
from .state import PDFStateStack, PDFColorSpace
from .state.Curves import CurveMethod, CurvePath, CurvePoint
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 RepeatedCommand(cmd_name)
@classmethod
def add(cls, *cmd_names: List[str]):
+12 -3
View File
@@ -1,5 +1,6 @@
from typing import List
from pdfmajor.execptions import CommandProcessorError
from pdfmajor.parser.PDFContentParser import PDFContentParser, PDFStream
from pdfmajor.parser.PSStackParser import PSKeyword, keyword_name
from pdfmajor.utils import get_logger
@@ -17,8 +18,6 @@ from .utils import init_resources
log = get_logger('process_command_stream')
class CommandProcessorError(Exception): pass
def process_command_stream(streams: List[PDFStream], font_cache: dict = None, state: PDFStateStack = None):
if font_cache is None:
font_cache = {}
@@ -27,6 +26,10 @@ def process_command_stream(streams: List[PDFStream], font_cache: dict = None, st
if isinstance(obj, PSKeyword):
name = keyword_name(obj)
method = name.replace('*', '_a').replace('"', '_w').replace("'", '_q')
func = None
args = []
if method == "Do":
pass
if method in PDFCommands.commands.keys():
func = PDFCommands.commands.get(method)
nargs = func.__code__.co_argcount-1
@@ -40,8 +43,12 @@ def process_command_stream(streams: List[PDFStream], font_cache: dict = None, st
func(state)
else:
log.debug('Unknown operator: %r (i.e. %r)' % (name, method))
# history.write(name,
# None if func is None else func.__name__
# , args)
else:
state.argstack.append(obj)
# history.write('arg', None, obj)
for complete_item in state.complete_layout_items:
if isinstance(complete_item, LTXObject):
@@ -51,6 +58,7 @@ def process_command_stream(streams: List[PDFStream], font_cache: dict = None, st
resources=complete_item.resources,
font_cache=font_cache
)
xobj_state.graphics = state.graphics.copy()
for item in process_command_stream(
[complete_item.stream],
font_cache=font_cache,
@@ -60,9 +68,10 @@ 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
+10 -9
View File
@@ -1,3 +1,4 @@
from pdfmajor.execptions import InvalidOperation
from pdfmajor.utils import mult_matrix, MATRIX_IDENTITY, apply_matrix_pt, get_logger
from pdfmajor.parser.PSStackParser import literal_name
from pdfmajor.parser.PDFStream import PDFStream, list_value, dict_value
@@ -253,7 +254,7 @@ 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 InvalidOperation('Undefined ColorSpace: %r' % name)
# setcolorspace-non-strokine
@PDFCommands.add('cs')
@@ -262,7 +263,7 @@ 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 InvalidOperation('Undefined ColorSpace: %r' % name)
# setgray-stroking
@PDFCommands.add('G')
@@ -326,7 +327,7 @@ 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 InvalidOperation('No colorspace specified!')
components = stack.pop(stack.graphics.scolspace.ncomponents)
stack.graphics.set_stroke_color(
stack.graphics.scolspace,
@@ -337,7 +338,7 @@ 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 InvalidOperation('No colorspace specified!')
components = stack.pop(stack.graphics.ncolspace.ncomponents)
stack.graphics.set_nostroke_color(
stack.graphics.ncolspace,
@@ -353,7 +354,7 @@ 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 InvalidOperation("Last TextBlock did not clear")
return stack
@PDFCommands.add('ET')
@@ -394,7 +395,7 @@ 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 InvalidOperation('Undefined Font id: %r' % fontid)
# setrendering
@PDFCommands.add('Tr')
@@ -444,9 +445,9 @@ 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 InvalidOperation("No Font Specified")
if stack.current_textblock is None:
raise PDFCommands.InvalidOperation("No TextBlock initilized")
raise InvalidOperation("No TextBlock initilized")
stack.current_textblock.add_char_block(
seq,
stack.t_matrix,
@@ -487,7 +488,7 @@ 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 InvalidOperation('Undefined xobject id: %r' % xobjid)
# log.info('Processing xobj: %r', xobj)
subtype = xobj.get('Subtype')
if subtype is LITERAL_FORM and 'BBox' in xobj:
@@ -1,10 +1,10 @@
from typing import List
from typing import Tuple, Optional
from .PDFColorSpace import PDFColorSpace
class PDFColor:
def __init__(self, color_space: PDFColorSpace, *values: List[float]):
self.color_space: PDFColorSpace = color_space
self.values: list = values
def __init__(self, color_space: Optional[PDFColorSpace], *values: float):
self.color_space: Optional[PDFColorSpace] = color_space
self.values: Tuple[float, ...] = values
def copy(self):
return self.__class__(
@@ -1,3 +1,4 @@
from typing import Dict
from collections import OrderedDict
class PDFColorSpace(object):
@@ -5,13 +6,12 @@ class PDFColorSpace(object):
def __init__(self, name: str, ncomponents: int):
self.name: str = name
self.ncomponents: int = ncomponents
return
def __repr__(self):
return '<PDFColorSpace: %s, ncomponents=%d>' % (self.name, self.ncomponents)
PREDEFINED_COLORSPACE = OrderedDict()
PREDEFINED_COLORSPACE: Dict[str, PDFColorSpace] = OrderedDict()
for (name, n) in [
('DeviceGray', 1), # default value first
@@ -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)
@@ -2,6 +2,7 @@
from abc import abstractmethod
from io import BytesIO
from pdfmajor.execptions import UnicodeNotDefined
from pdfmajor.parser.EncodingDB import EncodingDB
from pdfmajor.parser.PSStackParser import LIT
from pdfmajor.parser.PSStackParser import PSLiteral
@@ -10,11 +11,11 @@ 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
## Literals
##
LITERAL_STANDARD_ENCODING = LIT('StandardEncoding')
@@ -22,8 +23,6 @@ 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 +76,7 @@ class PDFFont(object):
except KeyError:
try:
return self.widths[self.to_unichr(cid)] * self.hscale
except (KeyError, self.PDFUnicodeNotDefined):
except (KeyError, UnicodeNotDefined):
return self.default_width * self.hscale
def char_disp(self, cid):
@@ -137,4 +136,4 @@ class PDFSimpleFont(PDFFont):
try:
return self.cid2unicode[cid]
except KeyError:
raise self.PDFUnicodeNotDefined(None, cid)
raise UnicodeNotDefined(None, cid)
@@ -1,13 +1,10 @@
## TrueTypeFont
##
import struct
from pdfmajor.execptions import CMapNotFound
from pdfmajor.parser.cmapdb import FileUnicodeMap
class TrueTypeFont(object):
class CMapNotFound(Exception):
pass
def __init__(self, name, fp):
self.name = name
self.fp = fp
@@ -27,7 +24,7 @@ class TrueTypeFont(object):
def create_unicode_map(self):
if 'cmap' not in self.tables:
raise TrueTypeFont.CMapNotFound
raise CMapNotFound
(base_offset, _) = self.tables['cmap']
fp = self.fp
fp.seek(base_offset)
@@ -1,5 +1,6 @@
from pdfmajor.execptions import PSEOF
from pdfmajor.parser.PSStackParser import PSStackParser
from pdfmajor.parser.PSStackParser import PSEOF, KWD
from pdfmajor.parser.PSStackParser import KWD
from pdfmajor.parser.PSStackParser import PSLiteral
from pdfmajor.parser.PSStackParser import literal_name
from pdfmajor.parser.EncodingDB import name2unicode
@@ -1,3 +1,4 @@
from pdfmajor.execptions import FontError
from pdfmajor.utils import get_logger, settings
from pdfmajor.parser.PSStackParser import literal_name
from pdfmajor.parser.PDFStream import list_value
@@ -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 FontError('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 FontError('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 FontError('Invalid Font spec: %r' % spec)
font = PDFType1Font(spec) # this is so wrong!
if objid:
cached_fonts[objid] = font
@@ -1,5 +1,6 @@
from io import BytesIO
from pdfmajor.execptions import FontError, UnicodeNotDefined, CMapNotFound
from pdfmajor.parser.PSStackParser import literal_name
from pdfmajor.parser.PDFStream import int_value
from pdfmajor.parser.PDFStream import num_value
@@ -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 FontError('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 FontError('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 FontError('Encoding is unspecified')
name = 'unknown'
try:
self.cmap = CMapDB.get_cmap(name)
except CMapDB.CMapNotFound as e:
except CMapNotFound as e:
if strict:
raise self.PDFFontError(e)
raise FontError(e)
self.cmap = CMap()
try:
descriptor = dict_value(spec['FontDescriptor'])
except KeyError:
if strict:
raise self.PDFFontError('FontDescriptor is missing')
raise FontError('FontDescriptor is missing')
descriptor = {}
ttf = None
if 'FontFile2' in descriptor:
@@ -123,12 +124,12 @@ class PDFCIDFont(PDFFont):
if ttf:
try:
self.unicode_map = ttf.create_unicode_map()
except TrueTypeFont.CMapNotFound:
except CMapNotFound:
pass
else:
try:
self.unicode_map = CMapDB.get_unicode_map(self.cidcoding, self.cmap.is_vertical())
except CMapDB.CMapNotFound as e:
except CMapNotFound as e:
pass
self.vertical = self.cmap.is_vertical()
@@ -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 UnicodeNotDefined(self.cidcoding, cid)
@@ -1,5 +1,6 @@
from .PDFFont import PDFFont, get_font
from pdfmajor.execptions import MissingFont, UnicodeNotDefined
from pdfmajor.utils import MATRIX_IDENTITY
from .PDFFont import PDFFont, get_font
## 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 MissingFont
try:
return self.font.to_unichr(cid)
except UnicodeNotDefined 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):
@@ -13,7 +13,7 @@ class LTComponent(LTItem):
if isinstance(bbox, Bbox):
self.bbox = bbox
else:
raise Exception("Invalid BBox")
raise AssertionError("Expected a BBox")
def __repr__(self):
return ('<%s %s>' %
@@ -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)
+3 -3
View File
@@ -4,11 +4,11 @@ import operator
from typing import List
from io import BytesIO
from pdfmajor.execptions import PSEOF, PSTypeError
from ..utils import int2byte, choplist, settings
from .PSStackParser import literal_name
from .PSStackParser import PSStackParser
from .PSStackParser import PSEOF, PSTypeError
from .PSStackParser import KWD
from .PDFStream import PDFStream
@@ -101,9 +101,9 @@ class PDFContentParser(PSStackParser):
obj = PDFStream(d, data)
self.push((pos, obj))
self.push((pos, self.KEYWORD_EI))
except PSTypeError:
except PSTypeError as e:
if settings.STRICT:
raise
raise e
else:
self.push((pos, token))
return
@@ -3,7 +3,6 @@ import hashlib as md5
from Crypto.Cipher import ARC4, AES
from Crypto.Hash import SHA256
from .exceptions import * # pylint: disable=W0614
from ..PDFStream import int_value, str_value, dict_value
from ..PSStackParser import literal_name
from ...utils import int2byte, struct
+7 -5
View File
@@ -1,18 +1,20 @@
import re
from logging import getLogger
from typing import Tuple, Optional, Dict
from pdfmajor.execptions import PSEOF, PDFSyntaxError
from ...utils import settings, choplist, nunpack
from ..PSStackParser import PSEOF
from ..PSStackParser import KWD
from ..PDFParser import PDFStreamParser
from ..PDFStream import PDFStream
from ..PDFStream import dict_value
from .constants import LITERAL_OBJSTM, LITERAL_XREF
from .exceptions import PDFNoValidXRef, PDFSyntaxError
log = getLogger(__name__)
Pos = Tuple[Optional[int], int, int]
## XRefs
##
@@ -27,7 +29,7 @@ class PDFBaseXRef(object):
# Must return
# (strmid, index, genno)
# or (None, pos, genno)
def get_pos(self, objid):
def get_pos(self, objid) -> Pos:
raise KeyError(objid)
@@ -36,7 +38,7 @@ class PDFBaseXRef(object):
class PDFXRef(PDFBaseXRef):
def __init__(self):
self.offsets = {}
self.offsets: Dict[int, Pos] = {}
self.trailer = {}
return
@@ -103,7 +105,7 @@ class PDFXRef(PDFBaseXRef):
try:
return self.offsets[objid]
except KeyError:
raise
raise
## PDFXRefFallback
+13 -5
View File
@@ -4,15 +4,23 @@ from Crypto.Cipher import ARC4, AES
from Crypto.Hash import SHA256
from logging import getLogger
from pdfmajor.execptions import (
ParserError,
PDFNoOutlines,
PDFDestinationNotFound,
PDFNoValidXRef,
PSEOF,
PDFObjectNotFound,
PDFTypeError,
PDFSyntaxError
)
from ...utils import settings, choplist, decode_text
from ..PSStackParser import KWD
from ..PSStackParser import literal_name
from ..PSStackParser import PSEOF
from ..PDFStream import int_value, str_value, dict_value, list_value, decipher_all
from ..PDFStream import PDFObjectNotFound, PDFTypeError
from ..PDFParser import PDFStreamParser, PDFStream, PDFSyntaxError
from ..PDFParser import PDFStreamParser, PDFStream
from .exceptions import *
from .PDFSecurityHandler import PDFStandardSecurityHandler
from .PDFSecurityHandler import PDFStandardSecurityHandlerV4
from .PDFSecurityHandler import PDFStandardSecurityHandlerV5
@@ -181,7 +189,7 @@ class PDFDocument(object):
def getobj(self, objid):
assert objid != 0
if not self.xrefs:
raise PDFException('PDFDocument is not initialized')
raise ParserError('PDFDocument is not initialized')
log.debug('getobj: objid=%r', objid)
if objid in self._cached_objs:
(obj, genno) = self._cached_objs[objid]
-22
View File
@@ -1,22 +0,0 @@
from ..PDFParser import PDFSyntaxError
from ..PDFStream import PDFException
## Exceptions
##
class PDFNoValidXRef(PDFSyntaxError):
pass
class PDFNoOutlines(PDFException):
pass
class PDFDestinationNotFound(PDFException):
pass
class PDFEncryptionError(PDFException):
pass
class PDFPasswordIncorrect(PDFEncryptionError):
pass
class PDFTextExtractionNotAllowed(PDFEncryptionError):
pass
+3 -2
View File
@@ -1,11 +1,12 @@
import logging
from pdfmajor.execptions import PDFTextExtractionNotAllowed, PDFObjectNotFound
from ..utils import settings
from .constants import LIT
from .PDFStream import PDFObjectNotFound
from .PDFStream import resolve1, int_value, list_value, dict_value
from .PDFParser import PDFParser
from .PDFDocument import PDFDocument, PDFTextExtractionNotAllowed
from .PDFDocument import PDFDocument
from ..utils import get_logger
+5 -9
View File
@@ -2,12 +2,13 @@
import logging
from io import BytesIO, TextIOWrapper
from ..utils import settings
from pdfmajor.execptions import (
PSSyntaxError,
PSEOF,
PDFSyntaxError
)
from .PSStackParser import PSStackParser
from .PSStackParser import PSSyntaxError
from .PSStackParser import PSEOF
from .PSStackParser import KWD
from .PDFStream import PDFException
from .PDFStream import PDFStream
from .PDFStream.PDFObjRef import PDFObjRef
from .PDFStream import int_value
@@ -16,11 +17,6 @@ from .PDFStream import dict_value
log = logging.getLogger(__name__)
## Exceptions
##
class PDFSyntaxError(PDFException):
pass
## PDFParser
##
+1 -2
View File
@@ -1,12 +1,11 @@
import zlib
from ..PSStackParser import PSException
from pdfmajor.execptions import PDFValueError, PDFObjectNotFound
from ..PSStackParser import PSObject
from ...utils import lzwdecode, settings
from .constants import * # pylint: disable=W0614
from .types import * # pylint: disable=W0614
from .exceptions import * # pylint: disable=W0614
## PDFObjRef
##
-1
View File
@@ -5,7 +5,6 @@ from ...utils import ascii85decode, asciihexdecode, apply_png_predictor
from .constants import *
from .types import *
from .exceptions import *
from .util import *
from .ccitt import ccittfaxdecode
+9 -17
View File
@@ -12,6 +12,7 @@
import sys
import array
from pdfmajor.execptions import EOFB, InvalidData, ByteSkip
from abc import abstractmethod
def get_bytes(data):
@@ -319,15 +320,6 @@ class CCITTG4Parser(BitParser):
BitParser.add(UNCOMPRESSED, 'T00000', '00000000011')
BitParser.add(UNCOMPRESSED, 'T10000', '00000000010')
class EOFB(Exception):
pass
class InvalidData(Exception):
pass
class ByteSkip(Exception):
pass
def __init__(self, width, bytealign=False):
BitParser.__init__(self)
self.width = width
@@ -340,10 +332,10 @@ class CCITTG4Parser(BitParser):
try:
for m in (128, 64, 32, 16, 8, 4, 2, 1):
self._parse_bit(byte & m)
except self.ByteSkip:
except ByteSkip:
self._accept = self._parse_mode
self._state = self.MODE
except self.EOFB:
except EOFB:
break
return
@@ -363,17 +355,17 @@ class CCITTG4Parser(BitParser):
self._accept = self._parse_uncompressed
return self.UNCOMPRESSED
elif mode == 'e':
raise self.EOFB
raise EOFB
elif isinstance(mode, int):
self._do_vertical(mode)
self._flush_line()
return self.MODE
else:
raise self.InvalidData(mode)
raise InvalidData(mode)
def _parse_horiz1(self, n):
if n is None:
raise self.InvalidData
raise InvalidData
self._n1 += n
if n < 64:
self._n2 = 0
@@ -386,7 +378,7 @@ class CCITTG4Parser(BitParser):
def _parse_horiz2(self, n):
if n is None:
raise self.InvalidData
raise InvalidData
self._n2 += n
if n < 64:
self._color = 1-self._color
@@ -401,7 +393,7 @@ class CCITTG4Parser(BitParser):
def _parse_uncompressed(self, bits):
if not bits:
raise self.InvalidData
raise InvalidData
if bits.startswith('T'):
self._accept = self._parse_mode
self._color = int(bits[1])
@@ -449,7 +441,7 @@ class CCITTG4Parser(BitParser):
self._y += 1
self._reset_line()
if self.bytealign:
raise self.ByteSkip
raise ByteSkip
return
def _do_vertical(self, dx):
-16
View File
@@ -1,16 +0,0 @@
from ..PSStackParser import PSException
class PDFException(PSException):
pass
class PDFTypeError(PDFException):
pass
class PDFValueError(PDFException):
pass
class PDFObjectNotFound(PDFException):
pass
class PDFNotImplementedError(PDFException):
pass
-1
View File
@@ -1,6 +1,5 @@
from .PDFObjRef import PDFObjRef
from ...utils import settings, isnumber, int2byte
from .exceptions import PDFTypeError
from logging import getLogger
@@ -4,9 +4,10 @@ log = logging.getLogger(__name__)
from io import TextIOWrapper
from typing import List, Tuple, Union
from pdfmajor.execptions import PSEOF
from ...utils import int2byte
from .exceptions import PSEOF
from .constants import EOL, NONSPC, KWD, END_LITERAL, LIT, HEX
from .constants import SPC, HEX_PAIR
from .constants import END_NUMBER, END_STRING, END_KEYWORD, END_HEX_STRING
+9 -8
View File
@@ -1,11 +1,12 @@
import logging
from io import TextIOWrapper
from pdfmajor.execptions import PSSyntaxError, PSTypeError, PSEOF
from ...utils import choplist, settings
from .PSBaseParser import PSBaseParser
from .types import *
from .exceptions import *
from .constants import *
log = logging.getLogger(__name__)
@@ -121,9 +122,9 @@ class PSStackParser(PSBaseParser):
# end array
try:
self.push(self.end_type('a'))
except PSTypeError:
except PSTypeError as e:
if settings.STRICT:
raise
raise e
elif token == KEYWORD_DICT_BEGIN:
# begin dictionary
self.start_type(pos, 'd')
@@ -136,9 +137,9 @@ class PSStackParser(PSBaseParser):
# construct a Python dictionary.
d = dict((literal_name(k), v) for (k, v) in choplist(2, objs) if v is not None)
self.push((pos, d))
except PSTypeError:
except PSTypeError as e:
if settings.STRICT:
raise
raise e
elif token == KEYWORD_PROC_BEGIN:
# begin proc
self.start_type(pos, 'p')
@@ -146,16 +147,16 @@ class PSStackParser(PSBaseParser):
# end proc
try:
self.push(self.end_type('p'))
except PSTypeError:
except PSTypeError as e:
if settings.STRICT:
raise
raise e
elif isinstance(token,PSKeyword):
log.debug('do_keyword: pos=%r, token=%r, stack=%r', pos, token, self.curstack)
self.do_keyword(pos, token)
else:
log.error('unknown token: pos=%r, token=%r, stack=%r', pos, token, self.curstack)
self.do_keyword(pos, token)
raise Exception("unknown tokens")
raise PSSyntaxError("unknown tokens")
if self.context:
continue
else:
@@ -1,20 +0,0 @@
## PS Exceptions
##
class PSException(Exception):
pass
class PSEOF(PSException):
pass
class PSSyntaxError(PSException):
pass
class PSTypeError(PSException):
pass
class PSValueError(PSException):
pass
+7 -10
View File
@@ -19,10 +19,13 @@ import pickle as pickle
import struct
import logging
from pdfmajor.execptions import (
CMapNotFound,
PSEOF,
PSSyntaxError,
)
from ...utils import choplist, nunpack, name2unicode
from ..PSStackParser import PSStackParser
from ..PSStackParser import PSSyntaxError
from ..PSStackParser import PSEOF
from ..PSStackParser import PSLiteral
from ..PSStackParser import KWD
from ..PSStackParser import literal_name
@@ -30,9 +33,6 @@ from ..PSStackParser import literal_name
log = logging.getLogger(__name__)
class CMapError(Exception):
pass
## CMapBase
##
@@ -219,9 +219,6 @@ class CMapDB(object):
_cmap_cache = {}
_umap_cache = {}
class CMapNotFound(CMapError):
pass
@classmethod
def _load_data(klass, name):
name = name.replace("\0", "")
@@ -238,7 +235,7 @@ class CMapDB(object):
finally:
gzfile.close()
else:
raise CMapDB.CMapNotFound(name)
raise CMapNotFound(name)
@classmethod
def get_cmap(klass, name):
@@ -325,7 +322,7 @@ class CMapParser(PSStackParser):
self.cmap.use_cmap(CMapDB.get_cmap(literal_name(cmapname)))
except PSSyntaxError:
pass
except CMapDB.CMapNotFound:
except CMapNotFound:
pass
return
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 -3
View File
@@ -10,12 +10,19 @@ import sys
with open('README.md') as readme_file:
SETUP = {
"name": "pdfmajor",
"version": "1.3.6",
"version": "1.3.13",
"packages": find_packages(include=['pdfmajor*']),
"install_requires": [
'pycryptodome',
'chardet'
'pycryptodome==3.8.2',
'chardet==3.0.4',
'Pillow>=6.2.0'
],
'extras_require': {
'dev': [
'tqdm==4.32.1',
'mkdocs==1.0.4'
]
},
"description": 'PDF parser',
"long_description": readme_file.read(),
'long_description_content_type': 'text/markdown',
+4
View File
@@ -0,0 +1,4 @@
from unittest import TestLoader, TextTestRunner
tests = TestLoader().discover('./tests')
result = TextTestRunner(verbosity=20).run(tests)
-1
View File
@@ -1 +0,0 @@
../pdfmajor
Binary file not shown.
Binary file not shown.
BIN
View File
Binary file not shown.
+24
View File
@@ -0,0 +1,24 @@
from pathlib import Path
from unittest import TestCase, main
from pdfmajor.interpreter import PDFInterpreter
from pdfmajor.execptions import UnicodeNotDefined
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(UnicodeNotDefined):
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()
+16 -13
View File
@@ -1,6 +1,5 @@
import os
from tqdm import tqdm
from unittest import TestCase, main
# from pdfmajor.extractor import extract_items_from_pdf
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
@@ -15,7 +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])
@@ -23,13 +22,17 @@ def count_elms(file_path: str):
count += 1
return count
with tqdm(desc='Cache Test', total=len(FILES)*NUM_LOOPS) as waiter:
for file_name in FILES:
waiter.set_description(f"Cache Test - [{file_name}]")
file_path = os.path.join(INPUT_FOLDER, file_name)
last_count = count_elms(file_path)
for _ in range(NUM_LOOPS):
new_count = count_elms(file_path)
assert new_count == last_count
last_count = new_count
waiter.update()
class CachingTester(TestCase):
def test_cache(self):
for file_name in FILES:
self.subTest(name = file_name)
file_path = os.path.join(INPUT_FOLDER, file_name)
last_count = count_elms(file_path)
for _ in range(NUM_LOOPS):
new_count = count_elms(file_path)
self.assertEqual( new_count , last_count )
last_count = new_count
if __name__ == '__main__':
# Run Tests
main()
+115
View File
@@ -0,0 +1,115 @@
import os
from typing import List
from unittest import TestCase, main
# from pdfmajor.extractor import extract_items_from_pdf
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter.commands import LTCurve, PDFColor, LTXObject
from pdfmajor.interpreter.commands import PREDEFINED_COLORSPACE
CUR_PATH = os.path.dirname(os.path.dirname(__file__))
INPUT_FOLDER = os.path.join(
CUR_PATH, "tests/samples/pdf"
)
FILES = os.listdir(INPUT_FOLDER)
NUM_LOOPS = 10
class ColorTest(TestCase):
def run_test(self, file_path: str, curve_defs: List[List[PDFColor]]):
def run_once(item):
if isinstance(item, LTCurve):
t_stroke, t_fill = curve_defs.pop(0)
self.assertEqual( item.stroke.values, t_stroke.values )
self.assertEqual( item.stroke.color_space, t_stroke.color_space )
self.assertEqual( item.fill.values, t_fill.values )
self.assertEqual( item.fill.color_space, t_fill.color_space )
elif isinstance(item, LTXObject):
for c in item:
run_once(c)
for page in PDFInterpreter(file_path):
for item in page:
run_once(item)
def test_lorem_v3(self):
self.run_test(
os.path.join(INPUT_FOLDER, "lorem-v3.pdf"),
[
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207),
],
[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 0),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207),
],
[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 0),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 0, 0),
]
] +
([[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
]]*24)+
([[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 0),
]]*11)+
([[
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 128, 128, 128),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 0),
]]*5)+
[[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
]]
)
def test_lorem_v4(self):
self.run_test(
os.path.join(INPUT_FOLDER, "lorem-v4.pdf"),
[
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 64, 64, 64),
]
]
)
def test_lorem_v5(self):
self.run_test(
os.path.join(INPUT_FOLDER, "lorem-v5.pdf"),
[
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255),
],
[
PDFColor(None),
PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 128, 128, 128),
]
]
)
if __name__ == '__main__':
# Run Tests
main()
+37 -25
View File
@@ -3,13 +3,14 @@ import re
import os
import logging
from unittest import TestCase, main
from typing import List
from pdfmajor.converters import convert_file
from xml.etree import ElementTree
from json import load as json_load
from tqdm import tqdm
def rel_path(*arg: List[str]) -> str:
def rel_path(*arg: str) -> str:
return os.path.normpath(os.path.join(os.path.dirname(__file__), *arg))
EXTS = ['text', 'json','xml','html']
@@ -22,28 +23,39 @@ if not os.path.exists(OUTPUT_FOLDER):
files = os.listdir(INPUT_FOLDER)
TOTAL = len(files)*len(EXTS)
with tqdm(total=TOTAL) as waiter:
for idx, file_name in enumerate(files):
file_name_no_ext = re.sub(r'\.pdf$',"", file_name)
input_file_path = os.path.join(INPUT_FOLDER, file_name)
for ext in EXTS:
if not os.path.exists(os.path.join(OUTPUT_FOLDER, ext)):
os.makedirs(os.path.join(OUTPUT_FOLDER, ext))
output_file_path = os.path.join(OUTPUT_FOLDER, ext, file_name_no_ext + "." + ext)
if len(file_name) > len(file_name_no_ext):
waiter.set_description(f"Conversion test -- {file_name}")
convert_file(
input_file=input_file_path,
output_file=output_file_path,
out_type=ext,
debug_level=logging.WARN,
)
if ext == 'xml':
waiter.set_description(f" > testing format {file_name}")
ElementTree.parse(output_file_path)
elif ext == 'json':
waiter.set_description(f" > testing format {file_name}")
json_load(open(output_file_path, 'r'))
waiter.update()
waiter.set_description("Done")
class ConversionTest(TestCase):
def test_conversion(self):
# with tqdm(total=TOTAL) as waiter:
for idx, file_name in enumerate(files):
self.subTest(i=idx);
file_name_no_ext = re.sub(r'\.pdf$',"", file_name)
input_file_path = os.path.join(INPUT_FOLDER, file_name)
for ext in EXTS:
if not os.path.exists(os.path.join(OUTPUT_FOLDER, ext)):
os.makedirs(os.path.join(OUTPUT_FOLDER, ext))
output_file_path = os.path.join(OUTPUT_FOLDER, ext, file_name_no_ext + "." + ext)
if len(file_name) > len(file_name_no_ext):
# waiter.set_description(f"Conversion test -- {file_name}")
convert_file(
input_file=input_file_path,
output_file=output_file_path,
out_type=ext,
ignore_bad_chars=True,
debug_level=logging.WARN,
)
if ext == 'xml':
# waiter.set_description(f" > testing format {file_name}")
ElementTree.parse(output_file_path)
elif ext == 'json':
# waiter.set_description(f" > testing format {file_name}")
with open(output_file_path, 'r') as outf:
json_load(outf)
# waiter.update()
# waiter.set_description("Done")
if __name__ == '__main__':
# Run Tests
main()
+52 -30
View File
@@ -1,43 +1,60 @@
from contextlib import contextmanager
from unittest import TestCase, main
from typing import List, Tuple, Callable
from os import remove
from tempfile import mktemp
from pdfmajor.converters.writers.html import HTMLMaker
from tqdm import tqdm
# Make temp file
FILE_NAME = mktemp()
TestFunction = Callable[[HTMLMaker], str];
TESTS: List[Tuple[TestFunction, str]] = [];
with HTMLMaker(FILE_NAME) as html:
with html.elm("html", nolineend=True):
html.write("test")
assert(open(FILE_NAME, 'r').read() == """<html >
class HTMLTester(TestCase):
@contextmanager
def get_html(self):
with HTMLMaker(FILE_NAME) as html:
yield html
def compare(self, expected: str):
with open(FILE_NAME, 'r') as f:
self.assertEqual(f.read() , expected)
def test_html_basic(self):
with self.get_html() as html:
with html.elm("html", nolineend=True):
html.write("test")
self.compare("""<html >
test
</html>""")
with HTMLMaker(FILE_NAME) as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
assert(open(FILE_NAME, 'r').read() == """<html >
def test_html_with_attributes(self):
with self.get_html() as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
self.compare("""<html >
<head >
<meta http-equiv="Content-Type" content="text/html" />
</head>
</html>""")
with HTMLMaker(FILE_NAME) as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
with html.elm("body"):
with html.elm("h1", css={"color": "red"}):
html.write("Hello World")
assert(open(FILE_NAME, 'r').read() == """<html >
def test_html_with_children(self):
with self.get_html() as html:
with html.elm("html", nolineend=True):
with html.elm("head"):
html.singleton("meta", {
'http-equiv': "Content-Type",
'content': "text/html"
})
with html.elm("body"):
with html.elm("h1", css={"color": "red"}):
html.write("Hello World")
self.compare("""<html >
<head >
<meta http-equiv="Content-Type" content="text/html" />
</head>
@@ -48,13 +65,18 @@ assert(open(FILE_NAME, 'r').read() == """<html >
</body>
</html>""")
with HTMLMaker(FILE_NAME) as html:
with html.elm('style'):
html.write('''.page { position: relative; overflow: hidden;border: 1px black solid;}''')
assert(open(FILE_NAME, 'r').read() == """<style >
def test_html_with_css(self):
with self.get_html() as html:
with html.elm('style'):
html.write('''.page { position: relative; overflow: hidden;border: 1px black solid;}''')
self.compare("""<style >
.page { position: relative; overflow: hidden;border: 1px black solid;}
</style>
""")
# Clean up
remove(FILE_NAME)
if __name__ == '__main__':
# Run Tests
main()
# Clean up
remove(FILE_NAME)
+21 -14
View File
@@ -1,5 +1,5 @@
import os
from tqdm import tqdm
from unittest import TestCase, main
from pdfmajor.interpreter import LTImage, logging
from pdfmajor.interpreter import PageInterpreter, PDFInterpreter
@@ -19,16 +19,23 @@ OUTPUT_FOLDER = os.path.join(
if not os.path.exists(OUTPUT_FOLDER):
os.makedirs(OUTPUT_FOLDER)
for file_name in tqdm(FILES, desc='Image Writer Test'):
for page in PDFInterpreter(os.path.join(
CUR_PATH,
f"tests/samples/pdf/{file_name}.pdf"
), debug_level=logging.ERROR):
assert isinstance(page, PageInterpreter)
for item_idx, item in enumerate(page):
assert isinstance(item, LTItem)
if isinstance(item, LTImage):
item.save_image(
OUTPUT_FOLDER,
file_name=f'{file_name}_p{page.page_num}i{item_idx}'
)
class ImageTester(TestCase):
def test_image_extract(self):
for file_name in FILES:
self.subTest(file_name=file_name)
for page in PDFInterpreter(os.path.join(
CUR_PATH,
f"tests/samples/pdf/{file_name}.pdf"
), debug_level=logging.ERROR):
self.assertTrue( isinstance(page, PageInterpreter) )
for item_idx, item in enumerate(page):
self.assertTrue( isinstance(item, LTItem) )
if isinstance(item, LTImage):
item.save_image(
OUTPUT_FOLDER,
file_name=f'{file_name}_p{page.page_num}i{item_idx}'
)
if __name__ == '__main__':
# Run Tests
main()
+17 -10
View File
@@ -1,5 +1,5 @@
import os
from tqdm import tqdm
from unittest import TestCase, main
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter.commands import LTItem
@@ -11,12 +11,19 @@ INPUT_FOLDER = os.path.join(
)
FILES = os.listdir(INPUT_FOLDER)
for file_name in tqdm(FILES, desc="Interpreter Test"):
file_path = os.path.join(INPUT_FOLDER, file_name)
for page in PDFInterpreter(file_path, debug_level=logging.ERROR):
assert isinstance(page, PageInterpreter)
for item in page:
assert isinstance(item, LTItem)
if isinstance(item, LTCharBlock):
for char in item:
assert isinstance(char, LTChar)
class TestInterpreter(TestCase):
def test_pdfintp(self):
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, ignore_bad_chars=True):
self.assertTrue( isinstance(page, PageInterpreter) )
for item in page:
self.assertTrue( isinstance(item, LTItem) )
if isinstance(item, LTCharBlock):
for char in item:
self.assertTrue( isinstance(char, LTChar) )
if __name__ == '__main__':
# Run Tests
main()
+44 -49
View File
@@ -2,17 +2,12 @@
# -*- coding: utf-8 -*-
from nose.tools import assert_equal, assert_true, assert_false
from nose import SkipTest
import nose
import logging
import unittest
from pdfmajor.parser.PDFStream.ccitt import CCITTG4Parser
## Test cases
##
class TestCCITTG4Parser():
class TestCCITTG4Parser(unittest.TestCase):
def get_parser(self, bits):
parser = CCITTG4Parser(len(bits))
@@ -23,98 +18,98 @@ class TestCCITTG4Parser():
def test_b1(self):
parser = self.get_parser('00000')
parser._do_vertical(0)
assert_equal(parser._curpos, 0)
self.assertEqual(parser._curpos, 0)
return
def test_b2(self):
parser = self.get_parser('10000')
parser._do_vertical(-1)
assert_equal(parser._curpos, 0)
self.assertEqual(parser._curpos, 0)
return
def test_b3(self):
parser = self.get_parser('000111')
parser._do_pass()
assert_equal(parser._curpos, 3)
assert_equal(parser._get_bits(), '111')
self.assertEqual(parser._curpos, 3)
self.assertEqual(parser._get_bits(), '111')
return
def test_b4(self):
parser = self.get_parser('00000')
parser._do_vertical(+2)
assert_equal(parser._curpos, 2)
assert_equal(parser._get_bits(), '11')
self.assertEqual(parser._curpos, 2)
self.assertEqual(parser._get_bits(), '11')
return
def test_b5(self):
parser = self.get_parser('11111111100')
parser._do_horizontal(0, 3)
assert_equal(parser._curpos, 3)
self.assertEqual(parser._curpos, 3)
parser._do_vertical(1)
assert_equal(parser._curpos, 10)
assert_equal(parser._get_bits(), '0001111111')
self.assertEqual(parser._curpos, 10)
self.assertEqual(parser._get_bits(), '0001111111')
return
def test_e1(self):
parser = self.get_parser('10000')
parser._do_vertical(0)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(0)
assert_equal(parser._curpos, 5)
assert_equal(parser._get_bits(), '10000')
self.assertEqual(parser._curpos, 5)
self.assertEqual(parser._get_bits(), '10000')
return
def test_e2(self):
parser = self.get_parser('10011')
parser._do_vertical(0)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(2)
assert_equal(parser._curpos, 5)
assert_equal(parser._get_bits(), '10000')
self.assertEqual(parser._curpos, 5)
self.assertEqual(parser._get_bits(), '10000')
return
def test_e3(self):
parser = self.get_parser('011111')
parser._color = 0
parser._do_vertical(0)
assert_equal(parser._color, 1)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._color, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(-2)
assert_equal(parser._color, 0)
assert_equal(parser._curpos, 4)
self.assertEqual(parser._color, 0)
self.assertEqual(parser._curpos, 4)
parser._do_vertical(0)
assert_equal(parser._curpos, 6)
assert_equal(parser._get_bits(), '011100')
self.assertEqual(parser._curpos, 6)
self.assertEqual(parser._get_bits(), '011100')
return
def test_e4(self):
parser = self.get_parser('10000')
parser._do_vertical(0)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(-2)
assert_equal(parser._curpos, 3)
self.assertEqual(parser._curpos, 3)
parser._do_vertical(0)
assert_equal(parser._curpos, 5)
assert_equal(parser._get_bits(), '10011')
self.assertEqual(parser._curpos, 5)
self.assertEqual(parser._get_bits(), '10011')
return
def test_e5(self):
parser = self.get_parser('011000')
parser._color = 0
parser._do_vertical(0)
assert_equal(parser._curpos, 1)
self.assertEqual(parser._curpos, 1)
parser._do_vertical(3)
assert_equal(parser._curpos, 6)
assert_equal(parser._get_bits(), '011111')
self.assertEqual(parser._curpos, 6)
self.assertEqual(parser._get_bits(), '011111')
return
def test_e6(self):
parser = self.get_parser('11001')
parser._do_pass()
assert_equal(parser._curpos, 4)
self.assertEqual(parser._curpos, 4)
parser._do_vertical(0)
assert_equal(parser._curpos, 5)
assert_equal(parser._get_bits(), '11111')
self.assertEqual(parser._curpos, 5)
self.assertEqual(parser._get_bits(), '11111')
return
def test_e7(self):
@@ -122,8 +117,8 @@ class TestCCITTG4Parser():
parser._curpos = 2
parser._color = 1
parser._do_horizontal(2, 6)
assert_equal(parser._curpos, 10)
assert_equal(parser._get_bits(), '1111000000')
self.assertEqual(parser._curpos, 10)
self.assertEqual(parser._get_bits(), '1111000000')
return
def test_e8(self):
@@ -131,19 +126,19 @@ class TestCCITTG4Parser():
parser._curpos = 1
parser._color = 0
parser._do_vertical(0)
assert_equal(parser._curpos, 2)
self.assertEqual(parser._curpos, 2)
parser._do_horizontal(7, 0)
assert_equal(parser._curpos, 9)
assert_equal(parser._get_bits(), '101111111')
self.assertEqual(parser._curpos, 9)
self.assertEqual(parser._get_bits(), '101111111')
return
def test_m1(self):
parser = self.get_parser('10101')
parser._do_pass()
assert_equal(parser._curpos, 2)
self.assertEqual(parser._curpos, 2)
parser._do_pass()
assert_equal(parser._curpos, 4)
assert_equal(parser._get_bits(), '1111')
self.assertEqual(parser._curpos, 4)
self.assertEqual(parser._get_bits(), '1111')
return
def test_m2(self):
@@ -152,7 +147,7 @@ class TestCCITTG4Parser():
parser._do_vertical(-1)
parser._do_vertical(1)
parser._do_horizontal(1, 1)
assert_equal(parser._get_bits(), '011101')
self.assertEqual(parser._get_bits(), '011101')
return
def test_m3(self):
@@ -161,8 +156,8 @@ class TestCCITTG4Parser():
parser._do_pass()
parser._do_vertical(1)
parser._do_vertical(1)
assert_equal(parser._get_bits(), '00000001')
self.assertEqual(parser._get_bits(), '00000001')
return
if __name__ == '__main__':
nose.runmodule()
unittest.main()
+12 -14
View File
@@ -1,9 +1,7 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from nose.tools import assert_equal
from nose import SkipTest
import nose
from unittest import TestCase, main
#test of various compression/encoding modules (previously in doctests):
from pdfmajor.utils.ascii85 import ascii85decode, asciihexdecode
@@ -14,24 +12,24 @@ import binascii
def hex(b): return binascii.hexlify(b) #encode('hex')
def dehex(b): return binascii.unhexlify(b) #decode('hex')
class TestAscii85():
class TestAscii85(TestCase):
def test_ascii85decode(self):
#The sample string is taken from: http://en.wikipedia.org/w/index.php?title=Ascii85
assert_equal(ascii85decode(b'9jqo^BlbD-BleB1DJ+*+F(f,q'),b'Man is distinguished')
assert_equal(ascii85decode(b'E,9)oF*2M7/c~>'),b'pleasure.')
self.assertEqual(ascii85decode(b'9jqo^BlbD-BleB1DJ+*+F(f,q'),b'Man is distinguished')
self.assertEqual(ascii85decode(b'E,9)oF*2M7/c~>'),b'pleasure.')
def test_asciihexdecode(self):
assert_equal(asciihexdecode(b'61 62 2e6364 65'),b'ab.cde')
assert_equal(asciihexdecode(b'61 62 2e6364 657>'),b'ab.cdep')
assert_equal(asciihexdecode(b'7>'),b'p')
self.assertEqual(asciihexdecode(b'61 62 2e6364 65'),b'ab.cde')
self.assertEqual(asciihexdecode(b'61 62 2e6364 657>'),b'ab.cdep')
self.assertEqual(asciihexdecode(b'7>'),b'p')
class TestLzw():
class TestLzw(TestCase):
def test_lzwdecode(self):
assert_equal(lzwdecode(b'\x80\x0b\x60\x50\x22\x0c\x0c\x85\x01'),b'\x2d\x2d\x2d\x2d\x2d\x41\x2d\x2d\x2d\x42')
self.assertEqual(lzwdecode(b'\x80\x0b\x60\x50\x22\x0c\x0c\x85\x01'),b'\x2d\x2d\x2d\x2d\x2d\x41\x2d\x2d\x2d\x42')
class TestRunlength():
class TestRunlength(TestCase):
def test_rldecode(self):
assert_equal(rldecode(b'\x05123456\xfa7\x04abcde\x80junk'),b'1234567777777abcde')
self.assertEqual(rldecode(b'\x05123456\xfa7\x04abcde\x80junk'),b'1234567777777abcde')
if __name__ == '__main__':
nose.runmodule()
main()
+35 -45
View File
@@ -2,19 +2,15 @@
# -*- coding: utf-8 -*-
from nose.tools import assert_equal, assert_true, assert_false
from nose import SkipTest
import nose
import logging
from pdfmajor.parser.PSStackParser import KWD, LIT, PSBaseParser, PSEOF, PSStackParser
from unittest import TestCase, main
from io import BytesIO
from pdfmajor.parser.PSStackParser import KWD, LIT, PSBaseParser, PSStackParser
from pdfmajor.execptions import PSEOF
## Simplistic Test cases
##
class TestPSBaseParser:
TESTDATA = br'''%!PS
TESTDATA = br'''%!PS
begin end
" @ #
/a/BCD /Some_Name /foo#5f#xbaa
@@ -33,36 +29,32 @@ func/a/b{(c)do*}def
[ 1 (z) ! ]
<< /foo (bar) >>
'''
TOKENS = [
(5, KWD(b'begin')), (11, KWD(b'end')), (16, KWD(b'"')), (19, KWD(b'@')),
(21, KWD(b'#')), (23, LIT('a')), (25, LIT('BCD')), (30, LIT('Some_Name')),
(41, LIT('foo_xbaa')), (54, 0), (56, 1), (59, -2), (62, 0.5),
(65, 1.234), (71, b'abc'), (77, b''), (80, b'abc ( def ) ghi'),
(98, b'def \x00 4ghi'), (118, b'bach\\slask'), (132, b'foo\nbaa'),
(143, b'this % is not a comment.'), (170, b'foo\nbaa'), (180, b'foobaa'),
(191, b''), (194, b' '), (199, b'@@ '), (211, b'\xab\xcd\x00\x124\x05'),
(226, KWD(b'func')), (230, LIT('a')), (232, LIT('b')),
(234, KWD(b'{')), (235, b'c'), (238, KWD(b'do*')), (241, KWD(b'}')),
(242, KWD(b'def')), (246, KWD(b'[')), (248, 1), (250, b'z'), (254, KWD(b'!')),
(256, KWD(b']')), (258, KWD(b'<<')), (261, LIT('foo')), (266, b'bar'),
(272, KWD(b'>>'))
]
OBJS = [
(23, LIT('a')), (25, LIT('BCD')), (30, LIT('Some_Name')),
(41, LIT('foo_xbaa')), (54, 0), (56, 1), (59, -2), (62, 0.5),
(65, 1.234), (71, b'abc'), (77, b''), (80, b'abc ( def ) ghi'),
(98, b'def \x00 4ghi'), (118, b'bach\\slask'), (132, b'foo\nbaa'),
(143, b'this % is not a comment.'), (170, b'foo\nbaa'), (180, b'foobaa'),
(191, b''), (194, b' '), (199, b'@@ '), (211, b'\xab\xcd\x00\x124\x05'),
(230, LIT('a')), (232, LIT('b')), (234, [b'c']), (246, [1, b'z']),
(258, {'foo': b'bar'}),
]
TOKENS = [
(5, KWD(b'begin')), (11, KWD(b'end')), (16, KWD(b'"')), (19, KWD(b'@')),
(21, KWD(b'#')), (23, LIT('a')), (25, LIT('BCD')), (30, LIT('Some_Name')),
(41, LIT('foo_xbaa')), (54, 0), (56, 1), (59, -2), (62, 0.5),
(65, 1.234), (71, b'abc'), (77, b''), (80, b'abc ( def ) ghi'),
(98, b'def \x00 4ghi'), (118, b'bach\\slask'), (132, b'foo\nbaa'),
(143, b'this % is not a comment.'), (170, b'foo\nbaa'), (180, b'foobaa'),
(191, b''), (194, b' '), (199, b'@@ '), (211, b'\xab\xcd\x00\x124\x05'),
(226, KWD(b'func')), (230, LIT('a')), (232, LIT('b')),
(234, KWD(b'{')), (235, b'c'), (238, KWD(b'do*')), (241, KWD(b'}')),
(242, KWD(b'def')), (246, KWD(b'[')), (248, 1), (250, b'z'), (254, KWD(b'!')),
(256, KWD(b']')), (258, KWD(b'<<')), (261, LIT('foo')), (266, b'bar'),
(272, KWD(b'>>'))
]
OBJS = [
(23, LIT('a')), (25, LIT('BCD')), (30, LIT('Some_Name')),
(41, LIT('foo_xbaa')), (54, 0), (56, 1), (59, -2), (62, 0.5),
(65, 1.234), (71, b'abc'), (77, b''), (80, b'abc ( def ) ghi'),
(98, b'def \x00 4ghi'), (118, b'bach\\slask'), (132, b'foo\nbaa'),
(143, b'this % is not a comment.'), (170, b'foo\nbaa'), (180, b'foobaa'),
(191, b''), (194, b' '), (199, b'@@ '), (211, b'\xab\xcd\x00\x124\x05'),
(230, LIT('a')), (232, LIT('b')), (234, [b'c']), (246, [1, b'z']),
(258, {'foo': b'bar'}),
]
class TestPSBaseParser(TestCase):
def get_tokens(self, s):
from io import BytesIO
class MyParser(PSStackParser):
def flush(self):
self.add_results(*self.popall())
@@ -76,8 +68,6 @@ func/a/b{(c)do*}def
return r
def get_objects(self, s):
from io import BytesIO
class MyParser(PSStackParser):
def flush(self):
self.add_results(*self.popall())
@@ -91,18 +81,18 @@ func/a/b{(c)do*}def
return r
def test_1(self):
tokens = self.get_tokens(self.TESTDATA)
tokens = self.get_tokens(TESTDATA)
logging.info(tokens)
assert_equal(tokens, self.TOKENS)
self.assertEqual(tokens, TOKENS)
return
def test_2(self):
objs = self.get_objects(self.TESTDATA)
objs = self.get_objects(TESTDATA)
logging.info(objs)
assert_equal(objs, self.OBJS)
self.assertEqual(objs, OBJS)
return
if __name__ == '__main__':
#import logging,sys,os,six
#logging.basicConfig(level=logging.DEBUG, filename='%s_%d.%d.log'%(os.path.basename(__file__),sys.version_info[0],sys.version_info[1]))
nose.runmodule()
main()