5 Commits
Author SHA1 Message Date
ari 7722b99f70 Deployong new version - v1.1.4 2018-10-29 13:03:28 -04:00
ari 66b5fea65c - compatible xml-converter with char-blocks
- consitent attr naming convention for fonts
2018-10-29 13:03:11 -04:00
ari 659b19dae9 Deployong new version - v1.1.3 2018-10-29 12:51:48 -04:00
ari 337c1b4a76 - pulling out boldness from font
- better html converter
2018-10-29 12:51:34 -04:00
ari 76deefb9dc Deployong new version - v1.1.2 2018-10-28 23:52:59 -04:00
9 changed files with 105 additions and 65 deletions

No files matched your search

+1 -1
View File
@@ -1 +1 @@
v1.1.1 v1.1.4
+4
View File
@@ -8,6 +8,10 @@ sh bin/clean.sh
python setup.py sdist bdist_wheel python setup.py sdist bdist_wheel
git add .
git commit -m "Deployong new version - $(cat .version)"
git push
git tag $(cat .version) git tag $(cat .version)
git push -u origin $(cat .version) git push -u origin $(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, 1) __version__ = (1, 1, 4)
if __name__ == '__main__': if __name__ == '__main__':
print( print(
+40 -23
View File
@@ -42,8 +42,8 @@ class HTMLConverter(PDFConverter):
self.__current_width = None self.__current_width = None
self.write_header() self.write_header()
def write(self, text: str): def write(self, text: str, lineend: str = '\n', deep_space: str = ' '):
text = " "*self.__levels_deep + text + '\n' text = deep_space*self.__levels_deep + text + lineend
self.write_raw(text) self.write_raw(text)
def write_raw(self, text): def write_raw(self, text):
@@ -78,7 +78,13 @@ class HTMLConverter(PDFConverter):
self.__levels_deep -= 1 self.__levels_deep -= 1
@contextmanager @contextmanager
def place_elm_with_child(self, tag_name: str, attr_dict: Dict[str, str] = {}, css: Dict[str, str] = None): def place_elm_with_child(self, tag_name: str, attr_dict: Dict[str, str] = {}, css: Dict[str, str] = None, no_additional_char = False):
lineend = '\n'
deep_space = ' '
if no_additional_char:
lineend = ''
deep_space = ''
if css is not None: if css is not None:
attr_dict['style'] = ";".join([ attr_dict['style'] = ";".join([
f'{name}: {value}' f'{name}: {value}'
@@ -88,11 +94,11 @@ class HTMLConverter(PDFConverter):
f'{name}="{value}"' f'{name}="{value}"'
for name, value in attr_dict.items() for name, value in attr_dict.items()
]) ])
self.write(f"<{tag_name} {attrs}>") self.write(f"<{tag_name} {attrs}>", lineend=lineend)
self.__levels_deep += 1 self.__levels_deep += 1
yield yield
self.__levels_deep -= 1 self.__levels_deep -= 1
self.write(f"</{tag_name}>") self.write(f"</{tag_name}>", deep_space=deep_space)
def place_elm_close(self, tag_name: str, attr_dict: Dict[str, str] = {}, css: Dict[str, str] = None, as_childless = True): def place_elm_close(self, tag_name: str, attr_dict: Dict[str, str] = {}, css: Dict[str, str] = None, as_childless = True):
if css is not None: if css is not None:
@@ -201,28 +207,39 @@ class HTMLConverter(PDFConverter):
self.place_image(item) self.place_image(item)
elif isinstance(item, LTChar): elif isinstance(item, LTChar):
with self.place_elm_with_child('span', { 'class': 'char' }, { with self.place_elm_with_child('span', { 'class': 'char' }, {
'font-size': f'{item.size}px', 'width': item.width,
'font-family': item.fontname, 'min-width': item.width,
'font-weight': 'bold' if 'bold' in item.fontname.lower() else '', 'max-width': item.width,
'color': get_color(item.graphicstate.ncolor), 'height': item.height,
'position': 'absolute', 'min-height': item.height,
'left': f'{item.x0}', 'max-height': item.height,
'bottom': f'{item.y0}',
'transform': f'skew({item.font.italic_angle}deg, 0deg)'
}): }):
self.write(item.get_text()) self.write(item.get_text())
elif isinstance(item, LTCharBlock): elif isinstance(item, LTCharBlock):
with self.place_elm_with_child('span', { 'class': 'char-block' }, { with self.place_elm_with_child('span', { 'class': 'char-block' }, {
'font-size': f'{item.size}px', 'position': 'absolute',
'font-family': item.fontname, 'left': f'{item.x0}',
'font-weight': 'bold' if 'bold' in item.fontname.lower() else '', 'bottom': f'{item.y0}',
'color': get_color(item.graphicstate.ncolor), 'text-align': 'justify',
'position': 'absolute', 'font-size': f'{item.size}px',
'left': f'{item.x0}', 'font-family': item.fontname,
'bottom': f'{item.y0}', 'font-weight': item.font.font_weight,
'transform': f'skew({item.font.italic_angle}deg, 0deg)' 'color': get_color(item.graphicstate.ncolor),
}): 'width': item.width,
self.write(item.get_text()) '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)
render(ltpage) render(ltpage)
def close(self): def close(self):
+30 -17
View File
@@ -1,4 +1,5 @@
import logging import logging
import re
from typing import Dict from typing import Dict
@@ -30,6 +31,12 @@ def get_color(col: PDFGraphicStateColor):
return f'gray({color_val})' return f'gray({color_val})'
return "" return ""
FIRST_CAP_RE = re.compile('(.)([A-Z][a-z]+)')
ALL_CAP_RE = re.compile('([a-z0-9])([A-Z])')
def convert_capcase_to_camelcase(text: str) -> str:
s1 = FIRST_CAP_RE.sub(r'\1_\2', text)
return ALL_CAP_RE.sub(r'\1_\2', s1).lower()
class XMLConverter(PDFConverter): class XMLConverter(PDFConverter):
def __init__(self, def __init__(self,
rsrcmgr, rsrcmgr,
@@ -113,23 +120,29 @@ class XMLConverter(PDFConverter):
}) })
def place_text(self, char: LTChar): def place_text(self, char: LTChar):
tag_name = 'char' with self.place_elm_with_child('char', {
if isinstance(char, LTCharBlock): 'width': char.width,
tag_name = 'char-block' 'height': char.height,
attr = { }, no_additional_char=True):
'size': char.size,
"color": get_color(char.graphicstate.ncolor),
"x0": char.x0,
"x1": char.x1,
"y0": char.y0,
"y1": char.y1,
}
for key, value in char.font.descriptor.items():
if key != "Type" and "FontFile" not in key:
attr["font-" + key] = value
with self.place_elm_with_child(tag_name, attr, no_additional_char=True):
self.write(char.get_text(), lineend='', deep_space="") self.write(char.get_text(), lineend='', deep_space="")
def render_char_block(self, char_block: LTCharBlock):
attr = {
'size': char_block.size,
"color": get_color(char_block.graphicstate.ncolor),
"x0": char_block.x0,
"x1": char_block.x1,
"y0": char_block.y0,
"y1": char_block.y1,
"is_bold": char_block.font.is_bold,
}
for key, value in char_block.font.descriptor.items():
if key != "Type" and "FontFile" not in key:
attr[convert_capcase_to_camelcase(key)] = value
with self.place_elm_with_child("char-block", attr):
for char in char_block:
self.place_text(char)
def render_curve(self, item: LTCurve): def render_curve(self, item: LTCurve):
attr = { attr = {
"x0": item.x0, "x0": item.x0,
@@ -164,8 +177,8 @@ class XMLConverter(PDFConverter):
render(child) render(child)
elif isinstance(item, LTImage): elif isinstance(item, LTImage):
self.place_image(item) self.place_image(item)
elif isinstance(item, LTChar) or isinstance(item, LTCharBlock): elif isinstance(item, LTCharBlock):
self.place_text(item) self.render_char_block(item)
render(ltpage) render(ltpage)
def close(self): def close(self):
+13
View File
@@ -531,6 +531,19 @@ class PDFFont(object):
@abstractmethod @abstractmethod
def to_unichr(self, cid): def to_unichr(self, cid):
raise NotImplementedError raise NotImplementedError
@property
def font_weight(self):
if 'FontWeight' in self.descriptor.keys():
return self.descriptor['FontWeight']
elif 'bold' in self.fontname.lower():
return 'bold'
else:
return None
@property
def is_bold(self):
return self.font_weight == 'bold' or self.font_weight > 549
# PDFSimpleFont # PDFSimpleFont
+12 -22
View File
@@ -26,7 +26,7 @@ from .PDFGraphicState import PDFGraphicState
from .PDFTextState import PDFTextState from .PDFTextState import PDFTextState
from .PDFContentParser import PDFContentParser from .PDFContentParser import PDFContentParser
from ..utils import settings, mult_matrix, MATRIX_IDENTITY from ..utils import mult_matrix, MATRIX_IDENTITY
from .constants import LITERAL_FORM, LITERAL_IMAGE from .constants import LITERAL_FORM, LITERAL_IMAGE
from .types import CurvePoint, CurvePath from .types import CurvePoint, CurvePath
@@ -303,8 +303,7 @@ class PDFPageInterpreter(object):
try: try:
self.scs = self.csmap[literal_name(name)] self.scs = self.csmap[literal_name(name)]
except KeyError: except KeyError:
if settings.STRICT: raise PDFInterpreterError('Undefined ColorSpace: %r' % name)
raise PDFInterpreterError('Undefined ColorSpace: %r' % name)
return return
# setcolorspace-non-strokine # setcolorspace-non-strokine
@@ -312,8 +311,7 @@ class PDFPageInterpreter(object):
try: try:
self.ncs = self.csmap[literal_name(name)] self.ncs = self.csmap[literal_name(name)]
except KeyError: except KeyError:
if settings.STRICT: raise PDFInterpreterError('Undefined ColorSpace: %r' % name)
raise PDFInterpreterError('Undefined ColorSpace: %r' % name)
return return
# setgray-stroking # setgray-stroking
@@ -357,9 +355,7 @@ class PDFPageInterpreter(object):
if self.scs: if self.scs:
n = self.scs.ncomponents n = self.scs.ncomponents
else: else:
if settings.STRICT: raise PDFInterpreterError('No colorspace specified!')
raise PDFInterpreterError('No colorspace specified!')
n = 1
self.pop(n) self.pop(n)
return return
@@ -367,9 +363,7 @@ class PDFPageInterpreter(object):
if self.ncs: if self.ncs:
n = self.ncs.ncomponents n = self.ncs.ncomponents
else: else:
if settings.STRICT: raise PDFInterpreterError('No colorspace specified!')
raise PDFInterpreterError('No colorspace specified!')
n = 1
self.pop(n) self.pop(n)
return return
@@ -432,6 +426,8 @@ class PDFPageInterpreter(object):
def do_Tw(self, space): def do_Tw(self, space):
self.textstate.wordspace = space self.textstate.wordspace = space
return return
# def do_Th(self, )
# textscale # textscale
def do_Tz(self, scale): def do_Tz(self, scale):
@@ -448,9 +444,8 @@ class PDFPageInterpreter(object):
try: try:
self.textstate.font = self.fontmap[literal_name(fontid)] self.textstate.font = self.fontmap[literal_name(fontid)]
except KeyError: except KeyError:
if settings.STRICT: raise PDFInterpreterError('Undefined Font id: %r' % fontid)
raise PDFInterpreterError('Undefined Font id: %r' % fontid) # self.textstate.font = self.rsrcmgr.get_font(None, {})
self.textstate.font = self.rsrcmgr.get_font(None, {})
self.textstate.fontsize = fontsize self.textstate.fontsize = fontsize
return return
@@ -495,9 +490,7 @@ class PDFPageInterpreter(object):
# show-pos # show-pos
def do_TJ(self, seq: bytearray): def do_TJ(self, seq: bytearray):
if self.textstate.font is None: if self.textstate.font is None:
if settings.STRICT: raise PDFInterpreterError('No font specified!')
raise PDFInterpreterError('No font specified!')
return
self.device.render_string(self.textstate.copy(), seq, self.ncs, self.graphicstate.copy()) self.device.render_string(self.textstate.copy(), seq, self.ncs, self.graphicstate.copy())
return return
@@ -540,9 +533,7 @@ class PDFPageInterpreter(object):
try: try:
xobj = PDFStream.validated_stream(self.xobjmap[xobjid]) xobj = PDFStream.validated_stream(self.xobjmap[xobjid])
except KeyError: except KeyError:
if settings.STRICT: raise PDFInterpreterError('Undefined xobject id: %r' % xobjid)
raise PDFInterpreterError('Undefined xobject id: %r' % xobjid)
return
log.info('Processing xobj: %r', xobj) log.info('Processing xobj: %r', xobj)
subtype = xobj.get('Subtype') subtype = xobj.get('Subtype')
if subtype is LITERAL_FORM and 'BBox' in xobj: if subtype is LITERAL_FORM and 'BBox' in xobj:
@@ -618,8 +609,7 @@ class PDFPageInterpreter(object):
log.debug('exec: %s', name) log.debug('exec: %s', name)
func() func()
else: else:
if settings.STRICT: raise PDFInterpreterError('Unknown operator: %r' % name)
raise PDFInterpreterError('Unknown operator: %r' % name)
else: else:
self.push(obj) self.push(obj)
return return
+3
View File
@@ -60,6 +60,9 @@ class LTCharBlock(LTComponent):
def __repr__(self): def __repr__(self):
return f"""<{self.__class__.__name__} font="{self.fontname}" text="{self.get_text()}"/>""" return f"""<{self.__class__.__name__} font="{self.fontname}" text="{self.get_text()}"/>"""
def __iter__(self):
return iter(self.chars)
def get_text(self): def get_text(self):
return "".join([ c.get_text() for c in self.chars ]) return "".join([ c.get_text() for c in self.chars ])
+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": "1.1.2", "version": "1.1.4",
"packages": find_packages(include=['pdfmajor*']), "packages": find_packages(include=['pdfmajor*']),
"install_requires": [ "install_requires": [
'pycryptodome', 'pycryptodome',