22 Commits
Author SHA1 Message Date
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
ari 14ba20be55 - better repr for curves and colors 2019-01-23 22:12:14 -05:00
ari 18938d91ea - better names for commands 2019-01-23 22:11:58 -05:00
ari eb38854076 updated gitinore 2019-01-23 22:11:46 -05:00
ari 671ae5bc4a running tests before every pip deploy 2019-01-23 22:10:51 -05:00
ari 844408c6e3 - ensured that all tests are working
- added a main test script
2019-01-23 22:06:12 -05:00
ari bab104885f - fixed caching error when running the interpreter multiple times on items with xobjects 2019-01-23 15:56:46 -05:00
ari 98f18c3e32 - corrected caching error
- added lorem ipsum pdf test docs
- introduced a new test for detecting if some unwanted caching is occuring
- muting "Unsupported" warning
2019-01-23 15:56:25 -05:00
ari ac2c462561 - improved html converter 2019-01-22 13:16:46 -05:00
ari 19712f1f0f cleaner html converter 2019-01-22 13:16:17 -05:00
ari ec02a7d38b - yaml converter
- adjusting curve detection
2019-01-16 16:56:14 -05:00
ari 0345ca01ba - slightly more accurate shape detection 2019-01-16 16:55:30 -05:00
ari b36f6bc907 silencing the unknown operator warning 2019-01-16 12:08:15 -05:00
ari f9f9a59793 - added yaml converter 2019-01-16 12:08:03 -05:00
ari b7026793d7 - minor bug fix -- xobj invalid name 2019-01-13 13:13:37 -05:00
ari addd59ed0f updated readme 2019-01-11 15:25:03 -05:00
42 changed files with 1113 additions and 449 deletions

No files matched your search

+4 -1
View File
@@ -10,4 +10,7 @@ tests/*.txt
.idea/
.vscode
tests/samples/output
**__pycache**
samples
**__pycache**\
.mypy_cache
.ipynb_checkpoints
+1 -1
View File
@@ -1 +1 @@
v1.3.2c
v1.3.8
+5 -5
View File
@@ -11,15 +11,15 @@
</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
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter import PDFInterpreter
for page in PDFInterpreter("/path/to/pdf.pdf"):
print("page start", page.page_num)
@@ -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
+12 -7
View File
@@ -6,13 +6,18 @@ cd ..
./bin/clean.sh
python setup.py sdist bdist_wheel
git add .
git commit
git push
if ./bin/run_tests.sh; then
python setup.py sdist bdist_wheel
git tag $(cat .version)
git push -u origin $(cat .version)
git add .
git commit
git push
twine upload dist/*
git tag $(cat .version)
git push -u origin $(cat .version)
twine upload dist/*
else
echo ">>> Stopped due to test failure!"
fi
+13
View File
@@ -0,0 +1,13 @@
#!/bin/bash
# Get working dir (this will make sure that the script will work the same anywhere you run it)
WK_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
cd $WK_DIR
cd ..
for filename in ./tests/test*.py; do
if python $filename ; then
echo woohoo
else
exit 1
fi
done
+2 -2
View File
@@ -24,7 +24,7 @@ See documentation [here](https://asosnovsky.github.io/pdfmajor/).
## Basic Example
```py
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter import PDFInterpreter
for page in PDFInterpreter("/path/to/pdf.pdf"):
print("page start", page.page_num)
@@ -97,7 +97,7 @@ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
"""
__version__ = (1, 3, 2c)
__version__ = (1, 3, 8)
if __name__ == '__main__':
print(
+23 -8
View File
@@ -2,33 +2,34 @@ import io
import os
import re
from typing import List
from typing import List, Optional
from .html import convert_to_html
from .xml import convert_to_xml
from .json import convert_to_json
from .text import convert_to_text
from .yaml import convert_to_yaml
from ..utils import logging
def convert_file(
input_file: str,
output_file: str = None,
image_folder_path: str = None,
output_file: Optional[str] = None,
image_folder_path: Optional[str] = None,
codec: str = 'utf-8',
maxpages: int = 0,
password: str = None,
password: Optional[str] = None,
caching: bool = True,
check_extractable: bool = True,
pagenos: List[int] = None,
pagenos: Optional[List[int]] = None,
dont_export_images: bool = False,
debug_level: int = logging.WARNING,
out_type: str = 'html',
):
if output_file is None:
output_file = os.path.join(
os.path.dirname(input_file.name),
os.path.dirname(input_file),
os.path.basename(
re.sub(r"\.\w+$", "."+out_type, input_file.name)
re.sub(r"\.\w+$", "."+out_type, input_file)
)
)
if re.search(re.escape(out_type) + r'$', output_file ) is None:
@@ -75,6 +76,20 @@ def convert_file(
dont_export_images=dont_export_images,
debug_level=debug_level,
)
elif out_type == 'yaml' or out_type == 'yml':
return convert_to_yaml(
input_file_path=input_file,
output_file_path=output_file,
image_folder_path=image_folder_path,
codec=codec,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=check_extractable,
pagenos=pagenos,
dont_export_images=dont_export_images,
debug_level=debug_level,
)
elif out_type == 'text':
return convert_to_text(
input_file_path=input_file,
@@ -89,4 +104,4 @@ def convert_file(
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'")
else: raise Exception("Please specify out_type as 'html' or 'xml' or 'json' or 'text' or 'yaml'")
+133 -102
View File
@@ -1,18 +1,20 @@
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
from ..interpreter.commands import LTItem
from ..interpreter.commands.state import CurvePath, PDFColor
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,
check_extractable: bool = True,
pagenos: List[int] = None,
@@ -43,19 +45,21 @@ def convert_to_html(
render_page(html, page)
def render_page(html: HTMLMaker, ltpage: PageInterpreter):
def render(item: LTItem):
def render(item: LTItem, block = True):
if isinstance(item, LTCurve):
render_curve(html, item)
render_curve(html, ltpage, item)
elif isinstance(item, LTXObject):
with html.elm('div', { "class": 'xobject' }, {
'position': 'absolute',
# 'position': 'absolute',
'left': f'{item.x0}px',
'right': f'{item.x1}px',
'bottom': f'{item.y0}px',
'top': f'{item.y1}px',
'width': f'{item.width}px',
'height': f'{item.height}px',
}):
for child in item:
render(child)
render(child, False)
elif isinstance(item, LTImage):
name = item.name
# if html.imagewriter is not None:
@@ -68,42 +72,42 @@ def render_page(html: HTMLMaker, ltpage: PageInterpreter):
})
elif isinstance(item, LTChar):
with html.elm('span', { 'class': 'char' }, {
'width': item.width,
'min-width': item.width,
'max-width': item.width,
'height': item.height,
'min-height': item.height,
'max-height': item.height,
'width': str(item.width) + "px",
'min-width': str(item.width) + "px",
'max-width': str(item.width) + "px",
'height': str(item.height) + "px",
'min-height': str(item.height) + "px",
'max-height': str(item.height) + "px",
}):
html.write(item.get_text())
elif isinstance(item, LTTextBlock):
for char in item:
render(char)
with html.elm('span', {'class': 'text-block'}):
for char in item:
render(char)
elif isinstance(item, LTCharBlock):
with html.elm('span', {'class': 'char-block'}):
with html.elm('p', { 'class': 'text-block' }, {
'position': 'absolute',
'left': f'{item.x0}',
'bottom': f'{item.y0}',
'font-size': f'{item.size}px',
'font-family': item.fontname,
'font-weight': item.font.font_weight,
'color': get_color(item.color, default="black"),
'width': item.width,
'min-width': item.width,
'max-width': item.width,
'height': item.height,
'min-height': item.height,
'max-height': item.height,
'transform': f'skew({item.font.italic_angle}deg, 0deg)',
'text-align': 'center',
'display': 'flex',
'flex-flow': 'row nowrap',
'justify-content': 'space-between',
# 'padding-left': item.font.leading
}):
for char in item:
render(char)
with html.elm('span', { 'class': 'char-block' }, {
'position': 'absolute',
'left': f'{item.x0}',
'bottom': f'{item.y0}',
'font-size': f'{item.size}px',
'font-family': item.fontname,
'font-weight': item.font.font_weight,
'color': get_color(item.color, default="black"),
'width': str(item.width) + "px",
'min-width': str(item.width) + "px",
'max-width': str(item.width) + "px",
'height': str(item.height) + "px",
'min-height': str(item.height) + "px",
'max-height': str(item.height) + "px",
'transform': f'skew({item.font.italic_angle}deg, 0deg)',
'text-align': 'center',
'display': 'flex',
'flex-flow': 'row nowrap',
'justify-content': 'space-between',
# 'padding-left': item.font.leading
}):
for char in item:
render(char)
with html.elm('div', { "class": 'page', "id": f"page-{ltpage.page_num}" }, {
'width': f'{ltpage.width}px',
@@ -125,69 +129,96 @@ def get_color(col: PDFColor, default: str = ""):
else:
return default
def render_curve(html: HTMLMaker, item: LTCurve):
css = {
'position': 'absolute',
'left': f'{item.x0}px',
'bottom': f'{item.y0}px',
'width': f'{item.width}px',
'height': f'{item.height}px',
}
path = ""
svg_attr = {
'class': 'curve',
'z-index': 2
}
path_css = {
def render_curve(html: HTMLMaker, ltpage: PageInterpreter, item: LTCurve):
path, svg_attr = create_svg_path(item)
stroke_col = get_color(item.stroke)
fill_col = get_color(item.fill)
path_css = {}
if fill_col:
path_css['fill'] = fill_col
if stroke_col:
path_css['stroke'] = stroke_col
}
# Compute ViewBox
p_vals = { "x": [], "y": [] }
for p in item.paths:
for pt in p.points:
p_vals['x'].append(pt.x)
p_vals['y'].append(pt.y)
mx_x = max([*p_vals['x'], 1])
mn_x = min([*p_vals['x'], 0])
mx_y = max([*p_vals['y'], 1])
mn_y = min([*p_vals['y'], 0])
if mx_x == mn_x:
mn_x -= 1
if mx_y == mn_y:
mn_y -= 1
dx = 1/( mx_x - mn_x )
dy = (item.height/item.width)/( mx_y - mn_y )
ROUND_VAL = 5
svg_attr.update({
# "viewBox": f"{min(p_vals['x'])} {min(p_vals['y'])} {max(p_vals['x'])} {max(p_vals['y'])}",
"viewBox": f"{round(mn_x*dx, ROUND_VAL)} {round(mn_y*dy, ROUND_VAL)} {round(mx_x*dx , ROUND_VAL)} {round(mx_y*dy, ROUND_VAL)}",
with html.elm('svg', svg_attr, css={
'border': '1px solid black',
'position': 'absolute',
'left': f'{item.x0}px',
'bottom': f'{ltpage.height - item.y0}px',
'top': f'{ltpage.height - item.y1}px',
'right': f'{item.x1}px',
'width': f'{item.width}px',
'height': f'{item.height}px',
}):
html.singleton('path', {
"d": path,
**path_css
}, {
**path_css
})
# Compute shape
for p in item.paths:
if p.method == CurvePath.METHOD.MOVE_TO:
path += f'M{" ".join( f"{round(dx*pt.x, ROUND_VAL)} {round(dy*pt.y, ROUND_VAL)}" for pt in p.points )} '
if p.method == CurvePath.METHOD.LINE_TO:
path += f'L{" ".join( f"{round(dx*pt.x, ROUND_VAL)} {round(dy*pt.y, ROUND_VAL)}" for pt in p.points )} '
if p.method == CurvePath.METHOD.CLOSE_PATH:
path += 'Z'
stroke_col = get_color(item.stroke)
fill_col = get_color(item.fill)
if fill_col:
path_css['fill'] = fill_col
if stroke_col:
path_css['stroke'] = stroke_col
with html.elm('svg', svg_attr, css):
html.singleton('path', {
"d": path,
**path_css
}, {
**path_css
})
def create_svg_path(item: LTCurve):
path = ""
svg_attr = {
'class': 'curve',
'z-index': 2
}
if item.height > 0:
dy = 1.0/item.height
dx = (item.width/item.height)/max([(item.x1-item.x0),0.01])
svg_attr.update({
"viewBox": "0 0 %s %s" % ( item.width/item.height, 1 )
})
else:
dx = 1.0/(item.x1-item.x0)
dy = 1.0
svg_attr.update({
"viewBox": "0 0 1 1"
})
if item.height > 1:
svg_attr.update({
'height': f'{item.height}px',
})
else:
svg_attr.update({
'height': '1px',
})
if item.width > 1:
svg_attr.update({
'width': f'{item.width}px',
})
else:
svg_attr.update({
'width': '1px',
})
def pX(val: float) -> float:
return ( val-item.x0 )*dx
def pY(val: float) -> float:
return ( item.height- (val-item.y0) )*dy
for p in item.paths:
if p.method == CurvePath.METHOD.MOVE_TO:
path += f'M{" ".join( f"{pX(p.x)} {pY(p.y)}" for p in p.points )} '
elif p.method == CurvePath.METHOD.LINE_TO:
path += f'L{" ".join( f"{pX(p.x)} {pY(p.y)}" for p in p.points )} '
elif p.method == CurvePath.METHOD.CLOSE_PATH:
path += 'Z'
elif p.method == CurvePath.METHOD.CURVE_BOTH_TO:
path += f'C{" ".join( f"{pX(pt.x)} {pY(pt.y)}" for pt in p.points )} '
return path, svg_attr
# def render_textblock(html: HTMLMaker, ltpage: PageInterpreter, item: LTTextBlock):
# (x0, y0, x1, y1) = (INF, INF, -INF, -INF)
# for c_block in item:
# x0 = min(x0, c_block.x0)
# y0 = min(y0, c_block.y0)
# x1 = max(x1, c_block.x1)
# y1 = max(y1, c_block.y1)
# with html.elm('span')
+4 -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 +21,14 @@ 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,
pagenos: Optional[List[int]] = None,
debug_level: int = logging.WARNING,
):
intepreter = PDFInterpreter(input_file_path,
+7 -7
View File
@@ -1,3 +1,4 @@
from typing import Optional
from io import TextIOWrapper
from contextlib import contextmanager
@@ -6,7 +7,7 @@ class HTMLMaker:
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')
@@ -42,21 +43,20 @@ 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):
with self.elm(tag_name, attrs, css, singleton=True):
def singleton(self, tag_name: str, attrs: dict = None, css: dict = None, singleton: bool = True):
with self.elm(tag_name, attrs, css, singleton=singleton):
pass
+6 -4
View File
@@ -1,3 +1,4 @@
from typing import Set
from json import dumps as json_dump
from io import TextIOWrapper
from contextlib import contextmanager
@@ -8,14 +9,13 @@ 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('{')
@@ -50,7 +50,8 @@ class JSONMakerObject:
self.write_prop(key, val)
def string(self, key: str, val: str):
self.write_prop(key, f'"{val}"')
val_sant = str(val).replace('"', '\\"')
self.write_prop(key, f'"{val_sant}"')
@contextmanager
def object(self, key: str):
@@ -109,7 +110,8 @@ class JSONMakerArray:
self.write_prop(val)
def string(self, val: str):
self.write_prop(f'"{val}"')
val_sant = str(val).replace('"', '\\"')
self.write_prop(f'"{val_sant}"')
@contextmanager
def object(self):
+117
View File
@@ -0,0 +1,117 @@
from json import dumps as json_dump
from io import TextIOWrapper
from contextlib import contextmanager
@contextmanager
def YAMLMaker(file_path: str, codec: str = 'utf-8'):
with open(file_path, 'wb') as outf:
with YAMLMakerObject(outf, codec=codec) as obj:
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
self.levels_deep = levels_deep
def __enter__(self):
if self.levels_deep > 0:
self.__write_raw('')
self.levels_deep += 1
return self
def __exit__(self, exc_type, exc_val, exc_tb):
self.levels_deep -= 1
def __write_raw(self, text):
if self.outfile is not None:
if self.codec:
text = text.encode(self.codec)
self.outfile.write(text)
else:
raise self.AccessError("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:
deep_space = ""
text = prefix + (deep_space*self.levels_deep) + text
self.__write_raw(text)
class YAMLMakerObject(YAMLMakerWriter):
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = -1, parent_is_array: bool = False):
YAMLMakerWriter.__init__(self, outfile, codec, levels_deep)
self.keys = set()
self.parent_is_array = parent_is_array
def write(self, key: str, value: str):
if key not in self.keys:
self.keys.add(key)
if len(self.keys) > 1:
self._write(f'{key}: {value}', prefix='\n')
else:
self._write(f'{key}: {value}', prefix='',
append_deep=not self.parent_is_array
)
@contextmanager
def object(self, key: str):
if key not in self.keys:
self.keys.add(key)
if len(self.keys) > 1:
self._write(f'{key}:\n', prefix='\n')
else:
self._write(f'{key}:\n', prefix='', append_deep=False)
with YAMLMakerObject(self.outfile, codec=self.codec, levels_deep=self.levels_deep) as obj:
yield obj
@contextmanager
def array(self, key: str):
if key not in self.keys:
self.keys.add(key)
if len(self.keys) > 1:
self._write(f'{key}:\n', prefix='\n')
else:
self._write(f'{key}:\n', prefix='')
with YAMLMakerArray(self.outfile, codec=self.codec, levels_deep=self.levels_deep) as obj:
yield obj
def place_object(self, key: str, obj: dict):
with self.object(key) as child:
for key, val in obj.items():
child.write(key, val)
def place_array(self, key: str, arr: list):
with self.array(key) as child:
for val in arr:
child.write(val)
class YAMLMakerArray(YAMLMakerWriter):
def __init__(self, outfile: TextIOWrapper, codec: str = 'utf-8', levels_deep: int = -1):
YAMLMakerWriter.__init__(self, outfile, codec, levels_deep)
self.childrencount = 0
def write(self, value: str = ""):
self.childrencount += 1
if self.childrencount > 1:
self._write(f'- {value}', prefix='\n')
else:
self._write(f'- {value}', prefix='')
@contextmanager
def object(self):
self.childrencount += 1
if self.childrencount > 1:
self._write(f'- ', prefix='\n')
else:
self._write(f'- ', prefix='')
with YAMLMakerObject(self.outfile, codec=self.codec, levels_deep=self.levels_deep, parent_is_array=True) as obj:
yield obj
def place_object(self, obj: dict):
with self.object() as child:
for key, val in obj.items():
child.write(key, val)
+144
View File
@@ -0,0 +1,144 @@
from typing import List
from .writers.yaml import YAMLMaker, YAMLMakerObject, YAMLMakerArray
from ..interpreter import PDFInterpreter, PageInterpreter, logging
from ..interpreter import LTImage, LTTextBlock, LTCharBlock, LTCurve, LTXObject
from ..interpreter.commands import LTItem
from ..interpreter.commands import LTRect, LTLine
from ..interpreter.commands.state import CurvePath, PDFColor
from ..parser.PSStackParser import PSLiteral
from ..utils import enc
def normalize_color_values(values: list):
ret = []
for v in values:
if isinstance(v, PSLiteral):
ret.append( enc(str(v.name)).decode() )
else:
ret.append( enc(str(v)).decode() )
return ret
def convert_to_yaml(
input_file_path: str,
output_file_path: str,
image_folder_path: str = None,
dont_export_images: bool = False,
codec: str = 'utf-8',
maxpages: int = 0,
password: str = None,
caching: bool = True,
check_extractable: bool = True,
pagenos: List[int] = None,
debug_level: int = logging.WARNING,
):
intepreter = PDFInterpreter(input_file_path,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=check_extractable,
pagenos=pagenos,
debug_level=debug_level
)
with YAMLMaker(output_file_path, codec=codec) as yaml:
with yaml.array("pages") as arr:
for page in intepreter:
with arr.object() as page_obj:
render_page(page_obj, page)
def render_page(yaml: YAMLMakerObject, ltpage: PageInterpreter):
yaml.write("id", ltpage.page_num)
yaml.write("width", ltpage.width)
yaml.write("height", ltpage.height)
with yaml.array("children") as chil_arr:
for child in ltpage:
with chil_arr.object() as chil_obj:
render(chil_obj, child)
def render(yaml: YAMLMakerObject, item: LTItem):
if isinstance(item, LTCurve):
place_curve(yaml, item)
elif isinstance(item, LTXObject):
yaml.write("type", 'xobject')
yaml.write("x0", item.x0)
yaml.write("x1", item.x1)
yaml.write("y0", item.y0)
yaml.write("y1", item.y1)
with yaml.array("children") as chil_arr:
for child in item:
with chil_arr.object() as chil_obj:
render(chil_obj, child)
elif isinstance(item, LTImage):
# if yaml.imagewriter is not None:
# name = yaml.imagewriter.export_image(item)
yaml.write("type", 'img')
yaml.write("src", enc(item.name, None))
yaml.write("x0", item.x0)
yaml.write("x1", item.x1)
yaml.write("y0", item.y0)
yaml.write("y1", item.y1)
elif isinstance(item, LTTextBlock):
place_text_block(yaml, item)
def place_text_block(yaml: YAMLMakerObject, text_block: LTTextBlock):
yaml.write("type", 'text-block')
yaml.write("x0", text_block.x0)
yaml.write("x1", text_block.x1)
yaml.write("y0", text_block.y0)
yaml.write("y1", text_block.y1)
with yaml.array("char_blocks") as cb_arr:
for cb in text_block:
with cb_arr.object() as cb_obj:
place_char_block(cb_obj, cb)
def place_char_block(yaml: YAMLMakerObject, char_block: LTCharBlock):
yaml.write("size", char_block.size)
yaml.write("x0", char_block.x0)
yaml.write("x1", char_block.x1)
yaml.write("y0", char_block.y0)
yaml.write("y1", char_block.y1)
if char_block.color.color_space is not None:
yaml.place_object("color", {
"type": enc(char_block.color.color_space.name).decode(),
"value": normalize_color_values(char_block.color.values)
})
for key, value in char_block.font.descriptor.items():
if key != "Type" and "FontFile" not in key:
yaml.write(key, value)
yaml.write("text",
"".join([
char.get_text()
for char in char_block
])
)
def place_curve(yaml: YAMLMakerObject, item: LTCurve):
if isinstance(item, LTRect):
yaml.write("type", 'rect')
elif isinstance(item, LTLine):
yaml.write("type", 'line')
else:
yaml.write("type", 'curve')
with yaml.array('paths') as paths_arr:
for path in item.paths:
paths_arr.place_object({
"type": path.method.name,
"points": [
{"x": point.x, "y": point.y}
for point in path.points
]
})
yaml.write("x0", item.x0)
yaml.write("x1", item.x1)
yaml.write("y0", item.y0)
yaml.write("y1", item.y1)
if item.fill.color_space is not None:
yaml.place_object("fill", {
"type": enc(item.fill.color_space.name).decode(),
"value": normalize_color_values(item.fill.values)
})
if item.stroke.color_space is not None:
yaml.place_object("stroke", {
"type": enc(item.stroke.color_space.name).decode(),
"value": normalize_color_values(item.stroke.values)
})
+13 -4
View File
@@ -20,15 +20,19 @@ 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 state is None:
state = PDFStateStack()
if font_cache is None:
font_cache = {}
parser = PDFContentParser(streams)
# from .cmd_record import CmdRecord
# history = CmdRecord()
for obj in parser:
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
@@ -41,18 +45,23 @@ def process_command_stream(streams: List[PDFStream], font_cache: dict = None, st
else:
func(state)
else:
log.warning('Unknown operator: %r (i.e. %r)' % (name, method))
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):
xobj_state = prep_state(
state=PDFGraphicState(),
state=PDFStateStack(),
ctm=complete_item.t_matrix,
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,
@@ -0,0 +1,9 @@
class CmdRecord:
def __init__(self, file_name: str = "./cmd_record"):
self.file = open(file_name, 'w')
self.file.write("c_name,func_name,args\n")
def write(self, c_name, func_name, args):
self.file.write(f"{c_name},{func_name},{args}\n")
def close(self):
self.file.close()
+94 -94
View File
@@ -14,42 +14,42 @@ log = get_logger('commands')
# No Support
# @PDFCommands.add('W','W_a', 'sh', 'ET', 'BX', 'EX' ,'BI', 'ID', 'gs')
# def do_no_support(stack: PDFStateStack) -> PDFStateStack:
# # log.warning("Unsupported command")
# # log.debug("Unsupported command")
# return stack
# marked content operators
@PDFCommands.add('MP')
def do_MP(stack: PDFStateStack, tag) -> PDFStateStack:
log.warning(f"Unsupported command - do_tag {[tag]}")
# self.device.do_tag(tag)
return stack
# @PDFCommands.add('MP')
# def do_MP(stack: PDFStateStack, tag) -> PDFStateStack:
# log.debug(f"Unsupported command - do_tag {[tag]}")
# # self.device.do_tag(tag)
# return stack
@PDFCommands.add('DP')
def do_DP(stack: PDFStateStack, tag, props=None) -> PDFStateStack:
log.warning(f"Unsupported command - do_tag {[tag.name, type(tag), props]}")
# self.device.do_tag(tag)
return stack
# @PDFCommands.add('DP')
# def do_DP(stack: PDFStateStack, tag, props=None) -> PDFStateStack:
# log.debug(f"Unsupported command - do_tag {[tag.name, type(tag), props]}")
# # self.device.do_tag(tag)
# return stack
@PDFCommands.add('BMC')
def do_BMC(stack: PDFStateStack, tag) -> PDFStateStack:
log.warning(f"Unsupported command - begin_tag {[tag.name, type(tag)]}")
# self.device.begin_tag(tag)
return stack
# @PDFCommands.add('BMC')
# def do_BMC(stack: PDFStateStack, tag) -> PDFStateStack:
# log.debug(f"Unsupported command - begin_tag {[tag.name, type(tag)]}")
# # self.device.begin_tag(tag)
# return stack
@PDFCommands.add('BDC')
def do_BDC(stack: PDFStateStack, tag, props=None) -> PDFStateStack:
log.warning(f"Unsupported command - begin_tag {[tag.name, type(tag), props]}")
# self.device.begin_tag(tag)
return stack
# @PDFCommands.add('BDC')
# def do_BDC(stack: PDFStateStack, tag, props=None) -> PDFStateStack:
# log.debug(f"Unsupported command - begin_tag {[tag.name, type(tag), props]}")
# # self.device.begin_tag(tag)
# return stack
@PDFCommands.add('EMC')
def do_EMC(stack: PDFStateStack) -> PDFStateStack:
# self.device.end_tag(tag)
log.warning("Unsupported command - end_tag")
return stack
# @PDFCommands.add('EMC')
# def do_EMC(stack: PDFStateStack) -> PDFStateStack:
# # self.device.end_tag(tag)
# log.debug("Unsupported command - end_tag")
# return stack
@PDFCommands.add('q')
def do_q(stack: PDFStateStack) -> PDFStateStack:
def save_state(stack: PDFStateStack) -> PDFStateStack:
stack.gstack.append([
stack.t_matrix,
stack.text.copy(),
@@ -58,136 +58,136 @@ def do_q(stack: PDFStateStack) -> PDFStateStack:
return stack
@PDFCommands.add('Q')
def do_Q(stack: PDFStateStack) -> PDFStateStack:
def restore_state(stack: PDFStateStack) -> PDFStateStack:
if len(stack.gstack) > 0:
stack.t_matrix, stack.text, stack.graphicstate = stack.gstack.pop()
return stack
# concat-matrix
@PDFCommands.add('cm')
def do_cm(stack: PDFStateStack, a1, b1, c1, d1, e1, f1) -> PDFStateStack:
def concat_transition_matrix(stack: PDFStateStack, a1, b1, c1, d1, e1, f1) -> PDFStateStack:
stack.t_matrix = mult_matrix((a1, b1, c1, d1, e1, f1), stack.t_matrix)
return stack
# setlinewidth
@PDFCommands.add('w')
def do_w(stack: PDFStateStack, linewidth) -> PDFStateStack:
def set_line_width(stack: PDFStateStack, linewidth) -> PDFStateStack:
stack.graphics.linewidth = linewidth
return stack
# setlinecap
@PDFCommands.add('J')
def do_J(stack: PDFStateStack, linecap) -> PDFStateStack:
def set_linecap(stack: PDFStateStack, linecap) -> PDFStateStack:
stack.graphics.linecap = linecap
return stack
# setlinejoin
@PDFCommands.add('j')
def do_j(stack: PDFStateStack, linejoin) -> PDFStateStack:
def set_linejoin(stack: PDFStateStack, linejoin) -> PDFStateStack:
stack.graphics.linejoin = linejoin
return stack
# setmiterlimit
@PDFCommands.add('M')
def do_M(stack: PDFStateStack, miterlimit) -> PDFStateStack:
def set_miterlimit(stack: PDFStateStack, miterlimit) -> PDFStateStack:
stack.graphics.miterlimit = miterlimit
return stack
# setdash
@PDFCommands.add('d')
def do_d(stack: PDFStateStack, dash, phase) -> PDFStateStack:
def set_dash(stack: PDFStateStack, dash, phase) -> PDFStateStack:
stack.graphics.dash = (dash, phase)
return stack
# setintent
@PDFCommands.add('ri')
def do_ri(stack: PDFStateStack, intent) -> PDFStateStack:
def set_intent(stack: PDFStateStack, intent) -> PDFStateStack:
stack.graphics.intent = intent
return stack
# setflatness
@PDFCommands.add('i')
def do_i(stack: PDFStateStack, flatness) -> PDFStateStack:
def set_flatness(stack: PDFStateStack, flatness) -> PDFStateStack:
stack.graphics.flatness = flatness
return stack
# moveto
@PDFCommands.add('m')
def do_m(stack: PDFStateStack, x: float, y: float) -> PDFStateStack:
def curve_moveto(stack: PDFStateStack, x: float, y: float) -> PDFStateStack:
stack.curvestacks.append(CurvePath(
CurvePath.METHOD.MOVE_TO,
CurvePoint(x, y)
CurvePoint(stack.t_matrix, x, y)
))
return stack
# lineto
@PDFCommands.add('l')
def do_l(stack: PDFStateStack, x: float, y: float) -> PDFStateStack:
def curve_lineto(stack: PDFStateStack, x: float, y: float) -> PDFStateStack:
stack.curvestacks.append(CurvePath(
CurvePath.METHOD.LINE_TO,
CurvePoint(x, y)
CurvePoint(stack.t_matrix, x, y)
))
return stack
# curveto
@PDFCommands.add('c')
def do_c(stack: PDFStateStack,
def curve_curveto(stack: PDFStateStack,
x1: float, y1: float,
x2: float, y2: float,
x3: float, y3: float ) -> PDFStateStack:
stack.curvestacks.append(CurvePath(
CurvePath.METHOD.CURVE_BOTH_TO,
CurvePoint(x1, y1),
CurvePoint(x2, y2),
CurvePoint(x3, y3),
CurvePoint(stack.t_matrix, x1, y1),
CurvePoint(stack.t_matrix, x2, y2),
CurvePoint(stack.t_matrix, x3, y3),
))
return stack
# urveto
@PDFCommands.add('v')
def do_v(stack: PDFStateStack,
def curve_urveto(stack: PDFStateStack,
x2: float, y2: float,
x3: float, y3: float) -> PDFStateStack:
stack.curvestacks.append(CurvePath(
CurvePath.METHOD.CURVE_NEXT_TO,
CurvePoint(x2, y2),
CurvePoint(x3, y3),
CurvePoint(stack.t_matrix, x2, y2),
CurvePoint(stack.t_matrix, x3, y3),
))
return stack
# rveto
@PDFCommands.add('y')
def do_y(stack: PDFStateStack,
def curve_rveto(stack: PDFStateStack,
x1: float, y1: float,
x3: float, y3: float) -> PDFStateStack:
stack.curvestacks.append(CurvePath(
CurvePath.METHOD.CURVE_FIRST_TO,
CurvePoint(x1, y1),
CurvePoint(x3, y3)
CurvePoint(stack.t_matrix, x1, y1),
CurvePoint(stack.t_matrix, x3, y3)
))
return stack
# closepath
@PDFCommands.add('h')
def do_h(stack: PDFStateStack) -> PDFStateStack:
def curve_close(stack: PDFStateStack) -> PDFStateStack:
stack.curvestacks.append(CurvePath(CurvePath.METHOD.CLOSE_PATH))
return stack
# rectangle
@PDFCommands.add('re')
def do_re(stack: PDFStateStack, x, y, w, h) -> PDFStateStack:
def curve_rect(stack: PDFStateStack, x, y, w, h) -> PDFStateStack:
stack.curvestacks.extend([
CurvePath(CurvePath.METHOD.MOVE_TO, CurvePoint(x, y) ),
CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(x+w, y) ),
CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(x+w, y+h) ),
CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(x, y+h) ),
CurvePath(CurvePath.METHOD.MOVE_TO, CurvePoint(stack.t_matrix, x, y) ),
CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(stack.t_matrix, x+w, y) ),
CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(stack.t_matrix, x+w, y+h) ),
CurvePath(CurvePath.METHOD.LINE_TO, CurvePoint(stack.t_matrix, x, y+h) ),
CurvePath(CurvePath.METHOD.CLOSE_PATH)
])
return stack
# stroke, fill
@PDFCommands.add('S', 'f', 'F', 'B')
def do_complete_path(stack: PDFStateStack) -> PDFStateStack:
def curve_complete_path(stack: PDFStateStack) -> PDFStateStack:
stack.complete_layout_items.append(make_curve(
stack.t_matrix,
stack.graphics.copy(),
@@ -199,7 +199,7 @@ def do_complete_path(stack: PDFStateStack) -> PDFStateStack:
# sroke, fill-even-odd
@PDFCommands.add('f_a', 'B_a')
def do_complete_path_evenodd(stack: PDFStateStack) -> PDFStateStack:
def curve_complete_path_evenodd(stack: PDFStateStack) -> PDFStateStack:
stack.complete_layout_items.append(make_curve(
stack.t_matrix,
stack.graphics.copy(),
@@ -211,7 +211,7 @@ def do_complete_path_evenodd(stack: PDFStateStack) -> PDFStateStack:
# close-and-stroke (do_h, do_S)
@PDFCommands.add('s', 'b')
def do_close_complete(stack: PDFStateStack) -> PDFStateStack:
def curve_close_complete(stack: PDFStateStack) -> PDFStateStack:
stack.curvestacks.append(CurvePath(
CurvePath.METHOD.CLOSE_PATH
))
@@ -226,7 +226,7 @@ def do_close_complete(stack: PDFStateStack) -> PDFStateStack:
# close-fill-and-stroke-even-odd
@PDFCommands.add('b_a')
def do_close_complete_evenodd(stack: PDFStateStack) -> PDFStateStack:
def curve_close_complete_evenodd(stack: PDFStateStack) -> PDFStateStack:
stack.curvestacks.append(CurvePath(
CurvePath.METHOD.CLOSE_PATH
))
@@ -241,14 +241,14 @@ def do_close_complete_evenodd(stack: PDFStateStack) -> PDFStateStack:
# close-only (empty path)
@PDFCommands.add('n')
def do_n(stack: PDFStateStack) -> PDFStateStack:
def curve_close_only(stack: PDFStateStack) -> PDFStateStack:
stack.curvestacks = []
return stack
# setcolorspace-stroking
@PDFCommands.add('CS')
def do_CS(stack: PDFStateStack, name: str) -> PDFStateStack:
def set_stroke_colorspace(stack: PDFStateStack, name: str) -> PDFStateStack:
try:
stack.graphics.scolspace = stack.colorspace_map[literal_name(name)]
return stack
@@ -257,7 +257,7 @@ def do_CS(stack: PDFStateStack, name: str) -> PDFStateStack:
# setcolorspace-non-strokine
@PDFCommands.add('cs')
def do_cs(stack: PDFStateStack, name: str) -> PDFStateStack:
def set_nonstroke_colorspace(stack: PDFStateStack, name: str) -> PDFStateStack:
try:
stack.graphics.ncolspace = stack.colorspace_map[literal_name(name)]
return stack
@@ -266,7 +266,7 @@ def do_cs(stack: PDFStateStack, name: str) -> PDFStateStack:
# setgray-stroking
@PDFCommands.add('G')
def do_G(stack: PDFStateStack, gray: float) -> PDFStateStack:
def set_stroke_gray(stack: PDFStateStack, gray: float) -> PDFStateStack:
stack.graphics.set_stroke_color(
stack.colorspace_map['DeviceGray'],
gray
@@ -275,7 +275,7 @@ def do_G(stack: PDFStateStack, gray: float) -> PDFStateStack:
# setgray-non-stroking
@PDFCommands.add('g')
def do_g(stack: PDFStateStack, gray: float) -> PDFStateStack:
def set_nonstroke_gray(stack: PDFStateStack, gray: float) -> PDFStateStack:
stack.graphics.set_nostroke_color(
stack.colorspace_map['DeviceGray'],
gray
@@ -285,7 +285,7 @@ def do_g(stack: PDFStateStack, gray: float) -> PDFStateStack:
# setrgb-stroking
@PDFCommands.add('RG')
def do_RG(stack: PDFStateStack, r, g, b) -> PDFStateStack:
def set_stroke_rgb(stack: PDFStateStack, r, g, b) -> PDFStateStack:
stack.graphics.set_stroke_color(
stack.colorspace_map['DeviceRGB'],
round(r*255),
@@ -296,7 +296,7 @@ def do_RG(stack: PDFStateStack, r, g, b) -> PDFStateStack:
# setrgb-non-stroking
@PDFCommands.add('rg')
def do_rg(stack: PDFStateStack, r, g, b) -> PDFStateStack:
def set_nonstroke_rgb(stack: PDFStateStack, r, g, b) -> PDFStateStack:
stack.graphics.set_nostroke_color(
stack.colorspace_map['DeviceRGB'],
round(r*255),
@@ -307,7 +307,7 @@ def do_rg(stack: PDFStateStack, r, g, b) -> PDFStateStack:
# setcmyk-stroking
@PDFCommands.add('K')
def do_K(stack: PDFStateStack, c, m, y, k) -> PDFStateStack:
def set_stroke_cmyk(stack: PDFStateStack, c, m, y, k) -> PDFStateStack:
stack.graphics.set_stroke_color(
stack.colorspace_map['DeviceCMYK'],
c, m, y, k
@@ -316,7 +316,7 @@ def do_K(stack: PDFStateStack, c, m, y, k) -> PDFStateStack:
# setcmyk-non-stroking
@PDFCommands.add('k')
def do_k(stack: PDFStateStack, c, m, y, k) -> PDFStateStack:
def set_nonstroke_cmyk(stack: PDFStateStack, c, m, y, k) -> PDFStateStack:
stack.graphics.set_stroke_color(
stack.colorspace_map['DeviceCMYK'],
c, m, y, k
@@ -324,7 +324,7 @@ def do_k(stack: PDFStateStack, c, m, y, k) -> PDFStateStack:
return stack
@PDFCommands.add('SCN','SC')
def do_SCN(stack: PDFStateStack) -> PDFStateStack:
def set_stroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
if stack.graphics.scolspace is None:
raise PDFCommands.InvalidOperation('No colorspace specified!')
components = stack.pop(stack.graphics.scolspace.ncomponents)
@@ -335,7 +335,7 @@ def do_SCN(stack: PDFStateStack) -> PDFStateStack:
return stack
@PDFCommands.add('scn','sc')
def do_scn(stack: PDFStateStack) -> PDFStateStack:
def set_nonstroke_colorspace_custom(stack: PDFStateStack) -> PDFStateStack:
if stack.graphics.ncolspace is None:
raise PDFCommands.InvalidOperation('No colorspace specified!')
components = stack.pop(stack.graphics.ncolspace.ncomponents)
@@ -347,7 +347,7 @@ def do_scn(stack: PDFStateStack) -> PDFStateStack:
# begin-text
@PDFCommands.add('BT')
def do_BT(stack: PDFStateStack) -> PDFStateStack:
def begin_text(stack: PDFStateStack) -> PDFStateStack:
stack.text.matrix = MATRIX_IDENTITY
stack.text.linematrix = [0, 0]
if stack.current_textblock is None:
@@ -357,38 +357,38 @@ def do_BT(stack: PDFStateStack) -> PDFStateStack:
return stack
@PDFCommands.add('ET')
def do_ET(stack: PDFStateStack) -> PDFStateStack:
def end_text(stack: PDFStateStack) -> PDFStateStack:
stack.complete_layout_items.append(stack.current_textblock)
stack.current_textblock = None
return stack
# setcharspace
@PDFCommands.add('Tc')
def do_Tc(stack: PDFStateStack, charspace) -> PDFStateStack:
def set_charspace(stack: PDFStateStack, charspace) -> PDFStateStack:
stack.text.charspace = charspace
return stack
# setwordspace
@PDFCommands.add('Tw')
def do_Tw(stack: PDFStateStack, wordspace) -> PDFStateStack:
def set_wordspace(stack: PDFStateStack, wordspace) -> PDFStateStack:
stack.text.wordspace = wordspace
return stack
# textscale
@PDFCommands.add('Tz')
def do_Tz(stack: PDFStateStack, scaling) -> PDFStateStack:
def set_textscale(stack: PDFStateStack, scaling) -> PDFStateStack:
stack.text.scaling = scaling
return stack
# setleading
@PDFCommands.add('TL')
def do_TL(stack: PDFStateStack, leading) -> PDFStateStack:
def set_text_leading(stack: PDFStateStack, leading) -> PDFStateStack:
stack.text.leading = -leading
return stack
# selectfont
@PDFCommands.add('Tf')
def do_Tf(stack: PDFStateStack, fontid, fontsize) -> PDFStateStack:
def set_font(stack: PDFStateStack, fontid, fontsize) -> PDFStateStack:
stack.text.fontsize = fontsize
try:
stack.text.font = stack.fontmap[literal_name(fontid)]
@@ -398,19 +398,19 @@ def do_Tf(stack: PDFStateStack, fontid, fontsize) -> PDFStateStack:
# setrendering
@PDFCommands.add('Tr')
def do_Tr(stack: PDFStateStack, render) -> PDFStateStack:
def set_text_rendering(stack: PDFStateStack, render) -> PDFStateStack:
stack.text.render = render
return stack
# settextrise
@PDFCommands.add('Ts')
def do_Ts(stack: PDFStateStack, rise) -> PDFStateStack:
def set_textrise(stack: PDFStateStack, rise) -> PDFStateStack:
stack.text.rise = rise
return stack
# text-move
@PDFCommands.add('Td')
def do_Td(stack: PDFStateStack, tx, ty) -> PDFStateStack:
def move_text_x(stack: PDFStateStack, tx, ty) -> PDFStateStack:
(a, b, c, d, e, f) = stack.text.matrix
stack.text.matrix = (a, b, c, d, tx*a+ty*c+e, tx*b+ty*d+f)
stack.text.linematrix = [0, 0]
@@ -418,7 +418,7 @@ def do_Td(stack: PDFStateStack, tx, ty) -> PDFStateStack:
# text-move
@PDFCommands.add('TD')
def do_TD(stack: PDFStateStack, tx, ty) -> PDFStateStack:
def move_text_y(stack: PDFStateStack, tx, ty) -> PDFStateStack:
(a, b, c, d, e, f) = stack.text.matrix
stack.text.matrix = (a, b, c, d, tx*a+ty*c+e, tx*b+ty*d+f)
stack.text.leading = ty
@@ -427,14 +427,14 @@ def do_TD(stack: PDFStateStack, tx, ty) -> PDFStateStack:
# textmatrix
@PDFCommands.add('Tm')
def do_Tm(stack: PDFStateStack, a, b, c, d, e, f) -> PDFStateStack:
def set_text_matrix(stack: PDFStateStack, a, b, c, d, e, f) -> PDFStateStack:
stack.text.matrix = (a, b, c, d, e, f)
stack.text.linematrix = [0, 0]
return stack
# nextline
@PDFCommands.add('T_a')
def do_T_a(stack: PDFStateStack) -> PDFStateStack:
def nextline(stack: PDFStateStack) -> PDFStateStack:
(a, b, c, d, e, f) = stack.text.matrix
stack.text.matrix = (a, b, c, d, stack.text.leading*c+e, stack.text.leading*d+f)
stack.text.linematrix = [0, 0]
@@ -442,7 +442,7 @@ def do_T_a(stack: PDFStateStack) -> PDFStateStack:
# show-pos
@PDFCommands.add('TJ')
def do_TJ(stack: PDFStateStack, seq: bytearray) -> PDFStateStack:
def add_char_blocks(stack: PDFStateStack, seq: bytearray) -> PDFStateStack:
if stack.text.font is None:
raise PDFCommands.InvalidOperation("No Font Specified")
if stack.current_textblock is None:
@@ -457,32 +457,32 @@ def do_TJ(stack: PDFStateStack, seq: bytearray) -> PDFStateStack:
# show
@PDFCommands.add('Tj')
def do_Tj(stack: PDFStateStack, b: bytes) -> PDFStateStack:
return do_TJ(stack, [b])
def add_char_block(stack: PDFStateStack, b: bytes) -> PDFStateStack:
return add_char_blocks(stack, [b])
# quote
@PDFCommands.add('_q')
def do__q(stack: PDFStateStack, b: bytes) -> PDFStateStack:
return do_TJ(do_T_a(stack), [b])
def add_quoted_char_blocks(stack: PDFStateStack, b: bytes) -> PDFStateStack:
return add_char_blocks(nextline(stack), [b])
# doublequote
@PDFCommands.add('_w')
def do__w(stack: PDFStateStack, wordspace, charspace, b) -> PDFStateStack:
def add_dbquoted_char_blocks(stack: PDFStateStack, wordspace, charspace, b) -> PDFStateStack:
stack.text.wordspace = wordspace
stack.text.charspace = charspace
return do_TJ(stack, [b])
return add_char_blocks(stack, [b])
@PDFCommands.add('EI')
def do_EI(stack: PDFStateStack, obj) -> PDFStateStack:
def insert_image(stack: PDFStateStack, obj) -> PDFStateStack:
if 'W' in obj and 'H' in obj:
stack.complete_layout_items.append(make_image(
obj, stack.ctm
obj, stack.t_matrix
))
return stack
# invoke an XObject
@PDFCommands.add('Do')
def do_Do(stack: PDFStateStack, xobjid) -> PDFStateStack:
def insert_xobject(stack: PDFStateStack, xobjid) -> PDFStateStack:
xobjid = literal_name(xobjid)
try:
xobj = PDFStream.validated_stream(stack.xobjmap[xobjid])
@@ -1,8 +1,14 @@
from enum import Enum
from typing import List
from pdfmajor.utils import apply_matrix_pt
class CurvePoint:
def __init__(self, x: float, y: float):
def __init__(self, ctm: tuple, x: float, y: float):
# old = (x,y)
# (x, y) = apply_matrix_pt(ctm, (x, y))
# if old != (x,y):
# print("CurvePoint", ctm, old)
# print(" >", x, y)
self.x = x
self.y = y
@@ -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__(
@@ -13,4 +13,6 @@ class PDFColor:
)
def __repr__(self):
return f"<PDFColor space={self.color_space} values={self.values}/>"
return f"""<PDFColor space="{
None if self.color_space is None else self.color_space.name
}" values={self.values}/>"""
@@ -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
@@ -24,6 +24,14 @@ class LTCurve(LTComponent):
self.stroke = stroke
self.fill = fill
def __repr__(self):
return ('<%s [%s] fill=%s stroke=%s>' % (
self.__class__.__name__,
str(self.bbox),
self.fill,
self.stroke
))
## LTLine
##
class LTLine(LTCurve):
@@ -90,9 +90,9 @@ class LTComponent(LTItem):
##
class LTContainer(LTComponent):
def __init__(self, bbox: Bbox, objs: List[LTItem] = []):
def __init__(self, bbox: Bbox, objs: List[LTItem] = None):
LTComponent.__init__(self, bbox)
self._objs: List[LTItem] = objs
self._objs: List[LTItem] = [] if objs is None else objs
return
def __iter__(self):
+4 -2
View File
@@ -1,5 +1,6 @@
import re
from logging import getLogger
from typing import Tuple, Optional, Dict
from ...utils import settings, choplist, nunpack
from ..PSStackParser import PSEOF
@@ -13,6 +14,7 @@ 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
+6
View File
@@ -13,6 +13,12 @@ class Bbox:
self.x1 = x1
self.y0 = y0
self.y1 = y1
if (x0 is not None) and (x1 is not None):
self.x0 = min([x0,x1])
self.x1 = max([x0,x1])
if (y0 is not None) and (y1 is not None):
self.y0 = min([y0,y1])
self.y1 = max([y0,y1])
@property
def height(self) -> float:
+10 -3
View File
@@ -10,12 +10,19 @@ import sys
with open('README.md') as readme_file:
SETUP = {
"name": "pdfmajor",
"version": "1.3.2c",
"version": "1.3.8",
"packages": find_packages(include=['pdfmajor*']),
"install_requires": [
'pycryptodome',
'chardet'
'pycryptodome==3.8.2',
'chardet==3.0.4',
'Pillow==6.0.0'
],
'extras_require': {
'dev': [
'tqdm==4.32.1',
'nose==1.3.7'
]
},
"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)
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
+38
View File
@@ -0,0 +1,38 @@
import os
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 LTContainer
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
def count_elms(file_path: str):
count = 0
for page in PDFInterpreter(file_path):
for item in page:
if isinstance(item, LTContainer):
count += len([*item])
else:
count += 1
return count
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()
+36 -27
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']
@@ -22,30 +23,38 @@ if not os.path.exists(OUTPUT_FOLDER):
files = os.listdir(INPUT_FOLDER)
TOTAL = len(files)*len(EXTS)
waiter = tqdm(total=TOTAL)
for idx, file_name in enumerate(files):
file_name_no_ext = re.sub(r'\.pdf$',"", file_name)
input_file_path = os.path.join(INPUT_FOLDER, file_name)
for ext in EXTS:
if not os.path.exists(os.path.join(OUTPUT_FOLDER, ext)):
os.makedirs(os.path.join(OUTPUT_FOLDER, ext))
output_file_path = os.path.join(OUTPUT_FOLDER, ext, file_name_no_ext + "." + ext)
if len(file_name) > len(file_name_no_ext):
waiter.set_description(f"Processing {file_name}")
convert_file(
input_file=input_file_path,
output_file=output_file_path,
out_type=ext,
debug_level=logging.WARN,
)
if ext == 'xml':
waiter.set_description(f" > testing format {file_name}")
ElementTree.parse(output_file_path)
elif ext == 'json':
waiter.set_description(f" > testing format {file_name}")
json_load(open(output_file_path, 'r'))
waiter.refresh()
waiter.update()
waiter.set_description("Done")
waiter.close()
class ConversionTest(TestCase):
def test_conversion(self):
# with tqdm(total=TOTAL) as waiter:
for idx, file_name in enumerate(files):
self.subTest(i=idx);
file_name_no_ext = re.sub(r'\.pdf$',"", 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,
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 -13
View File
@@ -1,4 +1,5 @@
import os
from unittest import TestCase, main
from pdfmajor.interpreter import LTImage, logging
from pdfmajor.interpreter import PageInterpreter, PDFInterpreter
@@ -18,16 +19,23 @@ OUTPUT_FOLDER = os.path.join(
if not os.path.exists(OUTPUT_FOLDER):
os.makedirs(OUTPUT_FOLDER)
for file_name in FILES:
for page in PDFInterpreter(os.path.join(
CUR_PATH,
f"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):
print(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()
+20 -12
View File
@@ -1,21 +1,29 @@
import os
# from pdfmajor.extractor import extract_items_from_pdf
from unittest import TestCase, main
from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging
from pdfmajor.interpreter import PageInterpreter
from pdfmajor.interpreter.commands import LTItem
from pdfmajor.interpreter.commands import LTCharBlock, LTChar
CUR_PATH = os.path.dirname(os.path.dirname(__file__))
FILE_NAME = os.path.join(
CUR_PATH,
"samples/pdf/tables.pdf"
INPUT_FOLDER = os.path.join(
CUR_PATH, "tests/samples/pdf"
)
FILES = os.listdir(INPUT_FOLDER)
for page in PDFInterpreter(FILE_NAME, debug_level=logging.INFO):
assert isinstance(page, PageInterpreter)
for item in page:
assert isinstance(item, LTItem)
if isinstance(item, LTCharBlock):
for char in item:
assert(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):
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()
-1
View File
@@ -80,7 +80,6 @@ with JSONMaker(FILE_NAME) as obj:
item.number("x1", 4.2)
item.number("y0", 231.12)
item.number("y1", 331.12)
print(open(FILE_NAME, 'r').read())
assert(open(FILE_NAME, 'r').read() == """{
"pages": [
{
+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()
+33 -44
View File
@@ -2,19 +2,14 @@
# -*- coding: utf-8 -*-
from nose.tools import assert_equal, assert_true, assert_false
from nose import SkipTest
import nose
import logging
from unittest import TestCase, main
from io import BytesIO
from pdfmajor.parser.PSStackParser import KWD, LIT, PSBaseParser, PSEOF, PSStackParser
## Simplistic Test cases
##
class TestPSBaseParser:
TESTDATA = br'''%!PS
TESTDATA = br'''%!PS
begin end
" @ #
/a/BCD /Some_Name /foo#5f#xbaa
@@ -33,36 +28,32 @@ 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 +67,6 @@ 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 +80,18 @@ 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()
+101
View File
@@ -0,0 +1,101 @@
from os import remove
from tempfile import mktemp
from pdfmajor.converters.writers.yaml import YAMLMaker
# Make temp file
FILE_NAME = mktemp()
with YAMLMaker(FILE_NAME) as yml:
yml.write("name", "bob")
yml.write("age", "20")
with yml.object("wife") as wife:
wife.write("name", "kory")
wife.write("age", "21")
with yml.array("children") as children:
with children.object() as child:
child.write("name", "Mike")
with child.array("toys") as toys:
toys.write("lion")
toys.write("bear")
with yml.object("computer") as computer:
computer.write("type", "awesome")
assert(open(FILE_NAME, 'r').read() == """name: bob
age: 20
wife:
name: kory
age: 21
children:
- name: Mike
toys:
- lion
- bear
computer:
type: awesome""")
with YAMLMaker(FILE_NAME) as yml:
yml.write("name", "bob")
yml.write("age", "20")
yml.place_object("wife", {
"name": "kory",
"age": 21
})
with yml.array("children") as children:
with children.object() as child:
child.write("name", "Mike")
child.place_array("toys", [
"lion", "bear"
])
yml.place_object("computer", {"type": "awesome"})
assert(open(FILE_NAME, 'r').read() == """name: bob
age: 20
wife:
name: kory
age: 21
children:
- name: Mike
toys:
- lion
- bear
computer:
type: awesome""")
with YAMLMaker(FILE_NAME) as yml:
with yml.array('pages') as pages:
with pages.object() as page:
page.write("id", 0)
page.write("width", 100)
page.write("height", 200)
with page.array("children") as children:
with children.object() as curve:
with curve.object("stroke") as fill:
fill.write("type", "DeviceRGB")
fill.write("value", ['1','2','3'])
curve.write("x0", 0)
curve.write("x1", 1)
with curve.object("fill") as fill:
fill.write("type", "DeviceRGB")
fill.write("value", ['1','2','3'])
curve.write("y0", 0)
curve.write("y1", 1)
assert(open(FILE_NAME, 'r').read() == """pages:
- id: 0
width: 100
height: 200
children:
- stroke:
type: DeviceRGB
value: ['1', '2', '3']
x0: 0
x1: 1
fill:
type: DeviceRGB
value: ['1', '2', '3']
y0: 0
y1: 1""")
# Clean up
remove(FILE_NAME)
+4 -5
View File
@@ -52,11 +52,10 @@ def main(args=None):
if len(parsed_args.files) == 1:
if parsed_args.output_file != "-":
func_args['output_file'] = open(parsed_args.output_file, "wb")
with open(parsed_args.files[0], 'rb') as input_file:
convert_file(
input_file,
**func_args
)
convert_file(
parsed_args.files[0],
**func_args
)
else:
print("Multiple files not supported yet.")
return 1