5 Commits
Author SHA1 Message Date
ari 5b641d6243 comment out leading for now 2018-10-29 16:35:32 -04:00
ari 10d679d379 clean up 2018-10-29 16:26:57 -04:00
ari 5378a4f34c - better color grabbing for scn
- show custom type in converters
2018-10-29 16:25:50 -04:00
ari 42cbc8e39e - using snake case
- not outputting is_bold
2018-10-29 13:18:12 -04:00
ari 66004988f4 actually cleaning it all prior to deployment 2018-10-29 13:04:32 -04:00
11 changed files with 59 additions and 26 deletions

No files matched your search

+1 -1
View File
@@ -1 +1 @@
v1.1.4 v1.1.5
+2 -2
View File
@@ -4,12 +4,12 @@ WK_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
cd $WK_DIR cd $WK_DIR
cd .. cd ..
sh bin/clean.sh ./bin/clean.sh
python setup.py sdist bdist_wheel python setup.py sdist bdist_wheel
git add . git add .
git commit -m "Deployong new version - $(cat .version)" git commit
git push git push
git tag $(cat .version) git tag $(cat .version)
+1 -1
View File
@@ -75,7 +75,7 @@ OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
""" """
__version__ = (1, 1, 4) __version__ = (1, 1, 5)
if __name__ == '__main__': if __name__ == '__main__':
print( print(
+4 -1
View File
@@ -26,6 +26,9 @@ def get_color(col: PDFGraphicStateColor):
return f"cmyk({','.join(map(str, color_val))})" return f"cmyk({','.join(map(str, color_val))})"
elif color_type == 'gray': elif color_type == 'gray':
return f'rgba(0,0,0,{1-color_val})' return f'rgba(0,0,0,{1-color_val})'
elif color_type == "custom":
# Todo: convert these to more friendly color types
return f"custom({col.custom['type']})"
return "none" return "none"
class HTMLConverter(PDFConverter): class HTMLConverter(PDFConverter):
@@ -236,7 +239,7 @@ class HTMLConverter(PDFConverter):
'display': 'flex', 'display': 'flex',
'flex-flow': 'row nowrap', 'flex-flow': 'row nowrap',
'justify-content': 'space-between', 'justify-content': 'space-between',
'padding-left': item.font.leading # 'padding-left': item.font.leading
}): }):
for char in item: for char in item:
render(char) render(char)
+8 -5
View File
@@ -1,5 +1,6 @@
import logging import logging
import re import re
import json
from typing import Dict from typing import Dict
@@ -29,13 +30,16 @@ def get_color(col: PDFGraphicStateColor):
return f"cmyk({','.join(map(str, color_val))})" return f"cmyk({','.join(map(str, color_val))})"
elif color_type == 'gray': elif color_type == 'gray':
return f'gray({color_val})' return f'gray({color_val})'
elif color_type == "custom":
# Todo: convert these to more friendly color types
return f"custom({col.custom['type']})"
return "" return ""
FIRST_CAP_RE = re.compile('(.)([A-Z][a-z]+)') FIRST_CAP_RE = re.compile('(.)([A-Z][a-z]+)')
ALL_CAP_RE = re.compile('([a-z0-9])([A-Z])') ALL_CAP_RE = re.compile('([a-z0-9])([A-Z])')
def convert_capcase_to_camelcase(text: str) -> str: def convert_capcase_to_snakecase(text: str) -> str:
s1 = FIRST_CAP_RE.sub(r'\1_\2', text) s1 = FIRST_CAP_RE.sub(r'\1-\2', text)
return ALL_CAP_RE.sub(r'\1_\2', s1).lower() return ALL_CAP_RE.sub(r'\1-\2', s1).lower()
class XMLConverter(PDFConverter): class XMLConverter(PDFConverter):
def __init__(self, def __init__(self,
@@ -134,11 +138,10 @@ class XMLConverter(PDFConverter):
"x1": char_block.x1, "x1": char_block.x1,
"y0": char_block.y0, "y0": char_block.y0,
"y1": char_block.y1, "y1": char_block.y1,
"is_bold": char_block.font.is_bold,
} }
for key, value in char_block.font.descriptor.items(): for key, value in char_block.font.descriptor.items():
if key != "Type" and "FontFile" not in key: if key != "Type" and "FontFile" not in key:
attr[convert_capcase_to_camelcase(key)] = value attr[convert_capcase_to_snakecase(key)] = value
with self.place_elm_with_child("char-block", attr): with self.place_elm_with_child("char-block", attr):
for char in char_block: for char in char_block:
self.place_text(char) self.place_text(char)
@@ -5,6 +5,7 @@ class PDFGraphicStateColor:
self.__rgb = None self.__rgb = None
self.__gray = None self.__gray = None
self.__cmyk = None self.__cmyk = None
self.__custom = None
def get_color(self): def get_color(self):
if self.__rgb is not None: if self.__rgb is not None:
@@ -13,6 +14,8 @@ class PDFGraphicStateColor:
return 'cmyk', self.cmyk return 'cmyk', self.cmyk
elif self.__gray is not None: elif self.__gray is not None:
return 'gray', self.gray return 'gray', self.gray
elif self.__custom is not None:
return 'custom', self.custom
else: return None, None else: return None, None
@property @property
@@ -34,6 +37,11 @@ class PDFGraphicStateColor:
if self.__gray is not None: return float(self.__gray) if self.__gray is not None: return float(self.__gray)
else: raise self.NotSet else: raise self.NotSet
@property
def custom(self):
if self.__custom is not None: return dict(self.__custom)
else: raise self.NotSet
@rgb.setter @rgb.setter
def rgb(self, rgb): def rgb(self, rgb):
self.__rgb = rgb self.__rgb = rgb
@@ -46,11 +54,16 @@ class PDFGraphicStateColor:
def gray(self, color): def gray(self, color):
self.__gray = color self.__gray = color
@custom.setter
def custom(self, color):
self.__custom = color
def copy(self): def copy(self):
cp = self.__class__() cp = self.__class__()
cp.gray = self.__gray cp.gray = self.__gray
cp.rgb = self.__rgb cp.rgb = self.__rgb
cp.cmyk = self.__cmyk cp.cmyk = self.__cmyk
cp.custom = self.__custom
return cp return cp
def __repr__(self): def __repr__(self):
@@ -58,4 +71,5 @@ class PDFGraphicStateColor:
if self.__gray is not None: rep += f' gray={self.__gray}' if self.__gray is not None: rep += f' gray={self.__gray}'
if self.__rgb is not None: rep += f' rgb=[{",".join(map(str, self.__rgb))}]' if self.__rgb is not None: rep += f' rgb=[{",".join(map(str, self.__rgb))}]'
if self.__cmyk is not None: rep += f' cmyk=[{",".join(map(str, self.__cmyk))}]' if self.__cmyk is not None: rep += f' cmyk=[{",".join(map(str, self.__cmyk))}]'
if self.__custom is not None: rep += f' custom={self.__custom}'
return rep + '/>' return rep + '/>'
+25 -11
View File
@@ -1,6 +1,7 @@
import logging import logging
import operator import operator
from collections import OrderedDict
from typing import List from typing import List
@@ -54,7 +55,7 @@ class PDFPageInterpreter(object):
self.resources = resources self.resources = resources
self.fontmap = {} self.fontmap = {}
self.xobjmap = {} self.xobjmap = {}
self.csmap = PREDEFINED_COLORSPACE.copy() self.csmap:OrderedDict = PREDEFINED_COLORSPACE.copy()
if not resources: if not resources:
return return
@@ -351,20 +352,33 @@ class PDFPageInterpreter(object):
return return
# setcolor # setcolor
def do_SCN(self): def __process_scn(self):
if self.scs:
n = self.scs.ncomponents
else:
raise PDFInterpreterError('No colorspace specified!')
self.pop(n)
return
def do_scn(self):
if self.ncs: if self.ncs:
n = self.ncs.ncomponents n = self.ncs.ncomponents
else: else:
raise PDFInterpreterError('No colorspace specified!') raise PDFInterpreterError('No colorspace specified!')
self.pop(n) components = self.pop(n)
obj_id = components[0]
if self.ncs.name not in self.resources.keys():
raise PDFInterpreterError("Color space not in resources")
if obj_id.name not in self.resources[self.ncs.name].keys():
raise PDFInterpreterError("Invalid Color reference")
color_data = self.resources[self.ncs.name][obj_id.name].resolve()
if isinstance(color_data, PDFStream):
color_data = color_data.attrs
return {
"type": self.ncs.name,
"defintion": color_data
}
def do_SCN(self):
self.graphicstate.scolor.custom = self.__process_scn()
return
def do_scn(self):
self.graphicstate.ncolor.custom = self.__process_scn()
return return
def do_SC(self): def do_SC(self):
+1 -1
View File
@@ -12,7 +12,7 @@ from .exceptions import * # pylint: disable=W0614
## ##
class PDFObjRef(PDFObject): class PDFObjRef(PDFObject):
def __init__(self, doc, objid, _): def __init__(self, doc, objid, a):
if objid == 0: if objid == 0:
if settings.STRICT: if settings.STRICT:
raise PDFValueError('PDF object id cannot be 0.') raise PDFValueError('PDF object id cannot be 0.')
@@ -100,7 +100,6 @@ class PSBaseParser(object):
linebuf += self.buf[self.charpos:] linebuf += self.buf[self.charpos:]
self.charpos = len(self.buf) self.charpos = len(self.buf)
log.debug('nextline: %r, %r', linepos, linebuf) log.debug('nextline: %r, %r', linepos, linebuf)
return (linepos, linebuf) return (linepos, linebuf)
def revreadlines(self): def revreadlines(self):
+2 -2
View File
@@ -16,9 +16,9 @@ if not os.path.exists(OUTPUT_FOLDER):
# files = os.listdir(INPUT_FOLDER) # files = os.listdir(INPUT_FOLDER)
# files = ['fonts.pdf'] # files = ['fonts.pdf']
# files = ['bar-charts.pdf'] files = ['bar-charts.pdf']
# files = ['font-color.pdf'] # files = ['font-color.pdf']
files = ['tables.pdf'] # files = ['tables.pdf']
TOTAL = len(files) TOTAL = len(files)
for idx, file_name in enumerate(files): for idx, file_name in enumerate(files):
+1 -1
View File
@@ -10,7 +10,7 @@ import sys
with open('README.md') as readme_file: with open('README.md') as readme_file:
SETUP = { SETUP = {
"name": "pdfmajor", "name": "pdfmajor",
"version": "1.1.4", "version": "1.1.5",
"packages": find_packages(include=['pdfmajor*']), "packages": find_packages(include=['pdfmajor*']),
"install_requires": [ "install_requires": [
'pycryptodome', 'pycryptodome',