def process_string(self, ts, array):
verbose('SHOW STRING ts: ', ts)
verbose('SHOW STRING array: ', array)
for obj in array:
verbose("processing obj: ", obj)
# this comes from TJ, number translates Tm
if utils.isnumber(obj):
Tj = obj
verbose("processing translation: ", Tj)
# translating Tm, change tx, ty according to direction
if ts.Tf.is_vertical():
tx = 0
ty = self.new_ty(0, Tj, ts.Tfs, 0, ts.Tw)
else:
tx = self.new_tx(0, Tj, ts.Tfs, 0, ts.Tw, ts.Th)
ty = 0
# update Tm accordingly
ts.Tm = utils.translate_matrix(ts.Tm, (tx, ty))
# there is an heuristic needed here, not sure what
# if -Tj > ts.Tf.char_width('o'):
# self.draw_cid(ts, 0, force_space=True)
else:
verbose("processing string")
for cid in ts.Tf.decode(obj):
self.draw_cid(ts, cid)
def filterObjs(obj, x, codec=None):
if obj is None:
return
if isinstance(obj, dict):
for (k, v) in six.iteritems(obj):
if (k == "URI"):
x.append(e(v))
filterObjs(v, x)
return
if isinstance(obj, list):
for v in obj:
filterObjs(v, x)
return
if isinstance(obj, (six.string_types, six.binary_type)):
return
if isinstance(obj, PDFStream):
return
if isinstance(obj, PDFObjRef):
return
if isinstance(obj, PSKeyword):
return
if isinstance(obj, PSLiteral):
return
if isnumber(obj):
return
raise TypeError(obj)
def render_string_horizontal(self, seq, matrix, pos,
font, fontsize, scaling, charspace, wordspace,
rise, dxscale, ncs, graphicstate):
(x, y) = pos
needcharspace = False
h_est = fontsize*matrix[3] # We estimate the size of the font by multiplying the fontsize by the height scaling in the textmatrix.
for obj in seq:
if utils.isnumber(obj):
x -= obj*dxscale
needcharspace = True
else:
for (char, cid) in zip(obj,font.decode(obj)):
if needcharspace:
x += charspace
char_width = self.render_char(utils.translate_matrix(matrix, (x, y)),
font, fontsize, scaling, rise, cid,
ncs, graphicstate)
self.push_char(bytes([char]), char_width, (x, y), h_est, font, matrix)
x += char_width
if cid == 32 and wordspace:
x += wordspace
needcharspace = True
# Push none to indicate end of rendering.
self.push_char(None, 0, (x,y), h_est, font, matrix)
return (x, y)
def dumpobj(self, out, obj):
if obj is None:
out.write(b'null ')
return
if isinstance(obj, dict):
out.write(b'<<')
for (k, v) in obj.items():
out.write(b'/%s ' % bytes(k, 'utf-8'))
self.dumpobj(out, v)
out.write(b'>>')
return
if isinstance(obj, list):
out.write(b'[')
for v in obj:
self.dumpobj(out, v)
out.write(b']')
return
if isinstance(obj, bytes):
out.write(b'(')
out.write(obj)
out.write(b')')
return
if isinstance(obj, str):
out.write(b'(')
out.write(bytes(e(obj), 'utf-8'))
out.write(b')')
return
if isinstance(obj, bool):
if obj:
out.write(b'true ')
else:
out.write(b'false ')
return
if isnumber(obj):
if isinstance(obj, float):
s = (b'%.5f ' % obj).rstrip(b'0')
else:
s = b'%d ' % obj
out.write(s)
return
if isinstance(obj, PDFObjRef):
out.write(b'%d 0 R ' % (obj.objid))
return
if isinstance(obj, PSKeyword):
out.write(b'/%s ' % bytes(obj.name, 'utf-8'))
return
if isinstance(obj, PSLiteral):
out.write(b'/%s ' % bytes(obj.name, 'utf-8'))
return
# if isinstance(obj, PDFStream):
raise TypeError(obj)
def dumpxml(out, obj, mode=None):
if obj is None:
out.write('<null />')
return
if isinstance(obj, dict):
out.write('<dict size="%d">\n' % len(obj))
for (k, v) in obj.items():
out.write('<key>%s</key>\n' % k)
out.write('<value>')
dumpxml(out, v)
out.write('</value>\n')
out.write('</dict>')
return
if isinstance(obj, list):
out.write('<list size="%d">\n' % len(obj))
for v in obj:
dumpxml(out, v)
out.write('\n')
out.write('</list>')
return
if isinstance(obj, bytes):
out.write('<string size="%d">%s</string>' % (len(obj), encode(obj)))
return
if isinstance(obj, PDFStream):
if mode == 'raw':
out.buffer.write(obj.get_rawdata())
elif mode == 'binary':
out.buffer.write(obj.get_data())
else:
out.write('<stream>\n<props>\n')
dumpxml(out, obj.attrs)
out.write('\n</props>\n')
if mode == 'text':
data = obj.get_data()
out.write('<data size="%d">%s</data>\n' %
(len(data), encode(data)))
out.write('</stream>')
return
if isinstance(obj, PDFObjRef):
out.write('<ref id="%d" />' % obj.objid)
return
if isinstance(obj, PSKeyword):
out.write('<keyword>%s</keyword>' % obj.name)
return
if isinstance(obj, PSLiteral):
out.write('<literal>%s</literal>' % obj.name)
return
if isnumber(obj):
out.write('<number>%s</number>' % obj)
return
raise TypeError(obj)
def dumpxml(out, obj, codec=None):
if obj is None:
out.write('<null />')
return
if isinstance(obj, dict):
out.write('<dict size="%d">\n' % len(obj))
for (k,v) in obj.iteritems():
out.write('<key>%s</key>\n' % k)
out.write('<value>')
dumpxml(out, v)
out.write('</value>\n')
out.write('</dict>')
return
if isinstance(obj, list):
out.write('<list size="%d">\n' % len(obj))
for v in obj:
dumpxml(out, v)
out.write('\n')
out.write('</list>')
return
if isinstance(obj, str):
out.write('<string size="%d">%s</string>' % (len(obj), e(obj)))
return
if isinstance(obj, PDFStream):
if codec == 'raw':
out.write(obj.get_rawdata())
elif codec == 'binary':
out.write(obj.get_data())
else:
out.write('<stream>\n<props>\n')
dumpxml(out, obj.attrs)
out.write('\n</props>\n')
if codec == 'text':
data = obj.get_data()
out.write('<data size="%d">%s</data>\n' % (len(data), e(data)))
out.write('</stream>')
return
if isinstance(obj, PDFObjRef):
out.write('<ref id="%d" />' % obj.objid)
return
if isinstance(obj, PSKeyword):
out.write('<keyword>%s</keyword>' % obj.name)
return
if isinstance(obj, PSLiteral):
out.write('<literal>%s</literal>' % obj.name)
return
if isnumber(obj):
out.write('<number>%s</number>' % obj)
return
raise TypeError(obj)
def dumpxml(out, obj, codec=None):
if obj is None:
out.write("<null />")
return
if isinstance(obj, dict):
out.write('<dict size="%d">\n' % len(obj))
for (k, v) in obj.items():
out.write("<key>%s</key>\n" % k)
out.write("<value>")
dumpxml(out, v)
out.write("</value>\n")
out.write("</dict>")
return
if isinstance(obj, list):
out.write('<list size="%d">\n' % len(obj))
for v in obj:
dumpxml(out, v)
out.write("\n")
out.write("</list>")
return
if isinstance(obj, ((str,), bytes)):
out.write('<string size="%d">%s</string>' % (len(obj), e(obj)))
return
if isinstance(obj, PDFStream):
if codec == "raw":
out.write(obj.get_rawdata())
elif codec == "binary":
out.write(obj.get_data())
else:
out.write("<stream>\n<props>\n")
dumpxml(out, obj.attrs)
out.write("\n</props>\n")
if codec == "text":
data = obj.get_data()
out.write('<data size="%d">%s</data>\n' % (len(data), e(data)))
out.write("</stream>")
return
if isinstance(obj, PDFObjRef):
out.write('<ref id="%d" />' % obj.objid)
return
if isinstance(obj, PSKeyword):
out.write("<keyword>%s</keyword>" % obj.name)
return
if isinstance(obj, PSLiteral):
out.write("<literal>%s</literal>" % obj.name)
return
if isnumber(obj):
out.write("<number>%s</number>" % obj)
return
raise TypeError(obj)
def dumpxml(out, obj, codec=None):
if obj is None:
out += '<null />'
return
if isinstance(obj, dict):
out += '<dict size="{}">\n'.format(len(obj))
for (k, v) in obj.items():
out += '<key>{}</key>\n'.format(k)
out += '<value>'
dumpxml(out, v)
out += '</value>\n'
out += '</dict>'
return out
if isinstance(obj, list):
out += '<list size="{}">\n'.format(len(obj))
for v in obj:
dumpxml(out, v)
out += '\n'
out += '</list>'
return out
if isinstance(obj, ((str,), bytes)):
out += '<string size="{}">{}</string>'.format(len(obj), e(obj))
return out
if isinstance(obj, PDFStream):
if codec == 'raw':
out += obj.get_rawdata()
elif codec == 'binary':
out += obj.get_data()
else:
out += '<stream>\n<props>\n'
dumpxml(out, obj.attrs)
out += '\n</props>\n'
if codec == 'text':
data = obj.get_data()
out += '<data size="{}">{}</data>\n'.format(len(data), e(data))
out += '</stream>'
return out
if isinstance(obj, PDFObjRef):
out += '<ref id="{}" />'.format(obj.objid)
return out
if isinstance(obj, PSKeyword):
out += '<keyword>{}</keyword>'.format(obj.name)
return out
if isinstance(obj, PSLiteral):
out += '<literal>{}</literal>'.format(obj.name)
return out
if isnumber(obj):
out += '<number>{}</number>'.format(obj)
return out
raise TypeError(obj)
def get_obj_type(obj):
if obj is None:
return None
if isinstance(obj, dict):
return 'dict'
if isinstance(obj, list):
return 'list'
if isinstance(obj, str):
return 'str'
if isinstance(obj, PDFStream):
return 'PDFStream'
if isinstance(obj, PDFObjRef):
return 'PDFObjRef'
if isinstance(obj, PSKeyword):
return 'PSKeyword'
if isinstance(obj, PSLiteral):
return 'PSLiteral'
if isnumber(obj):
return 'number'
return 'TypeError'
def dumpxml(obj, codec=None):
#print "dumpxml"
res = ""
if obj is None:
res += '<null />'
return res
if isinstance(obj, dict):
#print "dict"
res += '<dict size="%' + str(len(obj)) + '">\n'
for (k,v) in obj.iteritems():
#print "dict loop"
res += '<key>' + k + '</key>\n'
res += '<value>'
res += dumpxml( v)
#print "after v dump"
res += '</value>\n'
res += '</dict>'
#print "return dict"
return res
if isinstance(obj, list):
#print "list"
res += '<list size="' + str(len(obj)) + '">\n'
for v in obj:
#print "before list dump"
res += dumpxml(v)
#print "after list dump"
res += '\n'
res += '</list>'
return res
if isinstance(obj, str):
#print "string"
res += '<string size="' + str(len(obj)) + '">' + e(obj) + '</string>'
return res
if isinstance(obj, PDFStream):
#print "PDFStream"
if codec == 'raw':
res += obj.get_rawdata()
elif codec == 'binary':
res += obj.get_data()
else:
res += '<stream>\n<props>\n'
#print "before dump attrs"
res += dumpxml(obj.attrs)
#print "after dump attrs"
res += '\n</props>\n'
if codec == 'text':
data = obj.get_data()
res += '<data size="' + str(len(data)) + '">' + e(data) + '</data>\n'
res += '</stream>'
return res
if isinstance(obj, PDFObjRef):
#print "PDFObjRef"
res += '<ref id="' + str(obj.objid) + '" />'
return res
if isinstance(obj, PSKeyword):
#print "PSKeyword"
res += '<keyword>' + obj.name + '</keyword>'
return res
if isinstance(obj, PSLiteral):
#print "PSLiteral"
res += '<literal>' + obj.name + '</literal>'
return res
if isnumber(obj):
#print "Number " + str(obj)
res += '<number>' + str(obj) + '</number>'
return res
raise TypeError(obj)
def dump(self, obj):
res = ""
if obj is None:
res += '<null />'
return res
if isinstance(obj, dict):
res += '<dict size="%' + str(len(obj)) + '">\n'
for (k, v) in obj.iteritems():
k = re.sub(r'\W+', '', k)
if k.isdigit() or not k:
k = 'xml_creator_' + k
res += '<' + k + '>'
res += self.dump(v)
res += '</' + k + '>\n'
res += '</dict>'
return res
if isinstance(obj, list):
res += '<list size="' + str(len(obj)) + '">\n'
for v in obj:
res += self.dump(v)
res += '\n'
res += '</list>'
return res
if isinstance(obj, str):
self.check_js(obj)
# encode base64 to avoid illegal xml characters
res += '<string>' + self.e(obj).encode('base64') + '</string>'
return res
if isinstance(obj, PDFStream):
res += '<stream>\n'
try:
res += '<props>\n'
res += self.dump(obj.attrs)
res += '\n</props>\n'
data = obj.get_data()
self.check_js(str(data))
self.check_swf(str(data))
res += '<data size="' + str(len(data)) + '">' + self.e(
data).encode('base64') + '</data>\n'
# Throws an exception if the filter is unsupported, etc
except Exception as e:
# print e.message
res += '<StreamException>%s</StreamException>' % str(e)
# make sure the tag is closed appropriately
res += '</stream>'
return res
if isinstance(obj, PDFObjRef):
res += '<ref id="' + str(obj.objid) + '" />'
return res
if isinstance(obj, PSKeyword):
self.check_js(obj.name)
res += '<keyword>' + obj.name + '</keyword>'
return res
if isinstance(obj, PSLiteral):
self.check_js(obj.name)
res += '<literal>' + obj.name + '</literal>'
return res
if isnumber(obj):
self.check_js(str(obj))
res += '<number>' + str(obj) + '</number>'
return res
raise TypeError(obj)
def dumpxml(out, obj, codec=None):
if obj is None:
out.write('<null />')
return
if isinstance(obj, dict):
out.write('<dict size="%d">\n' % len(obj))
for (k, v) in obj.items():
out.write('<key>%s</key>\n' % k)
out.write('<value>')
dumpxml(out, v)
out.write('</value>\n')
out.write('</dict>')
return
if isinstance(obj, list):
out.write('<list size="%d">\n' % len(obj))
for v in obj:
dumpxml(out, v)
out.write('\n')
out.write('</list>')
return
if isinstance(obj, str):
out.write('<string size="%d">%s</string>' % (len(obj), e(obj)))
return
# added to avoid encoding errors
if isinstance(obj, bytes):
value = "".join(map(chr, obj))
out.write('<string size="%d">%s</string>' % (len(value), e(value)))
return
if isinstance(obj, PDFStream):
if codec == 'raw':
out.write(obj.get_rawdata())
elif codec == 'binary':
out.write(obj.get_data())
else:
out.write('<stream>\n<props>\n')
dumpxml(out, obj.attrs)
out.write('\n</props>\n')
if codec == 'text':
data = obj.get_data()
out.write('<data size="%d">%s</data>\n' % (len(data), e(data)))
out.write('</stream>')
return
if isinstance(obj, PDFObjRef):
out.write('<ref id="%d" />' % obj.objid)
return
if isinstance(obj, PSKeyword):
out.write('<keyword>%s</keyword>' % obj.name)
return
if isinstance(obj, PSLiteral):
out.write('<literal>%s</literal>' % obj.name)
return
if isnumber(obj):
out.write('<number>%s</number>' % obj)
return
# raise TypeError(obj)
print('Exception')
print(obj)
print(type(obj))
def dumpxml(out: TextIO, obj: object, codec: Optional[str] = None) -> None:
if obj is None:
out.write('<null />')
return
if isinstance(obj, dict):
out.write('<dict size="%d">\n' % len(obj))
for (k, v) in obj.items():
out.write('<key>%s</key>\n' % k)
out.write('<value>')
dumpxml(out, v)
out.write('</value>\n')
out.write('</dict>')
return
if isinstance(obj, list):
out.write('<list size="%d">\n' % len(obj))
for v in obj:
dumpxml(out, v)
out.write('\n')
out.write('</list>')
return
if isinstance(obj, (str, bytes)):
out.write('<string size="%d">%s</string>' % (len(obj), escape(obj)))
return
if isinstance(obj, PDFStream):
if codec == 'raw':
# Bug: writing bytes to text I/O. This will raise TypeError.
out.write(obj.get_rawdata()) # type: ignore [arg-type]
elif codec == 'binary':
# Bug: writing bytes to text I/O. This will raise TypeError.
out.write(obj.get_data()) # type: ignore [arg-type]
else:
out.write('<stream>\n<props>\n')
dumpxml(out, obj.attrs)
out.write('\n</props>\n')
if codec == 'text':
data = obj.get_data()
out.write('<data size="%d">%s</data>\n' %
(len(data), escape(data)))
out.write('</stream>')
return
if isinstance(obj, PDFObjRef):
out.write('<ref id="%d" />' % obj.objid)
return
if isinstance(obj, PSKeyword):
# Likely bug: obj.name is bytes, not str
out.write('<keyword>%s</keyword>' %
obj.name) # type: ignore [str-bytes-safe]
return
if isinstance(obj, PSLiteral):
# Likely bug: obj.name may be bytes, not str
out.write('<literal>%s</literal>' %
obj.name) # type: ignore [str-bytes-safe]
return
if isnumber(obj):
out.write('<number>%s</number>' % obj)
return
raise TypeError(obj)
def dump(self, obj):
res = ""
if obj is None:
res += '<null />'
return res
if isinstance(obj, dict):
res += '<dict size="%' + str(len(obj)) + '">\n'
for (k,v) in obj.iteritems():
k = re.sub(r'\W+', '', k)
if k.isdigit() or not k:
k = 'xml_creator_' + k
res += '<' + k + '>'
res += self.dump(v)
res += '</' + k + '>\n'
res += '</dict>'
return res
if isinstance(obj, list):
res += '<list size="' + str(len(obj)) + '">\n'
for v in obj:
res += self.dump(v)
res += '\n'
res += '</list>'
return res
if isinstance(obj, str):
self.check_js(obj)
#encode base64 to avoid illegal xml characters
res += '<string>' + self.e(obj).encode('base64') + '</string>'
return res
if isinstance(obj, PDFStream):
res += '<stream>\n'
try:
res += '<props>\n'
res += self.dump(obj.attrs)
res += '\n</props>\n'
data = obj.get_data()
self.check_js(str(data))
self.check_swf(str(data))
res += '<data size="' + str(len(data)) + '">' + self.e(data).encode('base64') + '</data>\n'
#Throws an exception if the filter is unsupported, etc
except Exception as e:
#print e.message
res += '<StreamException>%s</StreamException>' % str(e)
#make sure the tag is closed appropriately
res += '</stream>'
return res
if isinstance(obj, PDFObjRef):
res += '<ref id="' + str(obj.objid) + '" />'
return res
if isinstance(obj, PSKeyword):
self.check_js(obj.name)
res += '<keyword>' + obj.name + '</keyword>'
return res
if isinstance(obj, PSLiteral):
self.check_js(obj.name)
res += '<literal>' + obj.name + '</literal>'
return res
if isnumber(obj):
self.check_js(str(obj))
res += '<number>' + str(obj) + '</number>'
return res
raise TypeError(obj)
def show_string(self, ts, array):
verbose(ts)
sentence = []
word = []
m = (ts.Tfs * ts.Th, 0, 0, ts.Tfs, 0, ts.Trise)
applicable_Tm = utils.mult_matrix(m, ts.Tm)
(sx, _, _, sy, tx, ty) = applicable_Tm
current_state = (sx, sy, tx, ty)
if self.last_state == None:
self.paragraph = []
verbose('current paragraph becomes=', self.paragraph)
elif current_state[0] == self.last_state[0]:
verbose('DECISION: grouping the text object to last')
else:
verbose('DECISION: finalizing the paragraph')
key = self.last_state[0]
item = self.paragraph_map.get(key, '')
if len(item) > 0:
item = item = ' '
new_item = ' '.join(self.paragraph)
self.paragraph_map[key] = item + new_item
self.paragraph = []
verbose('current paragraph becomes=', self.paragraph)
self.last_state = current_state
for obj in array:
verbose("processing obj=", obj)
if utils.isnumber(obj):
Tj = obj
if Tj < WITHIN_WORD_MOVE_LIMIT:
verbose("DECISION: new word")
sentence.append(''.join(word))
verbose('current sentence becomes=', sentence)
word = []
verbose('current word becomes=', word)
else:
verbose("DECISION: move inside the current word")
if ts.Tf.is_vertical():
tx = 0
ty = ((Tj / 1000) * ts.Tfs)
else:
tx = ((Tj / 1000) * ts.Tfs) * ts.Th
ty = 0
ts.Tm = utils.mult_matrix((1, 0, 0, 1, tx, ty), ts.Tm)
else:
for cid in ts.Tf.decode(obj):
verbose("processing cid=", cid)
m = (ts.Tfs * ts.Th, 0, 0, ts.Tfs, 0, ts.Trise)
applicable_Tm = utils.mult_matrix(m, ts.Tm)
if cid == 32:
applicable_Tw = ts.Tw
sentence.append(''.join(word))
verbose('current sentence becomes=', sentence)
word = []
else:
try:
text = ts.Tf.to_unichr(cid)
except PDFUnicodeNotDefined:
if MISSING_CHAR:
text = MISSING_CHAR
else:
raise
word.append(text)
verbose('current word becomes=', word)
applicable_Tw = 0
w = ts.Tf.char_width(cid)
if ts.Tf.is_vertical():
tx = 0
ty = ((w - 0) * ts.Tfs + ts.Tc + applicable_Tw)
else:
tx = ((w - 0) * ts.Tfs + ts.Tc + applicable_Tw) * ts.Th
ty = 0
ts.Tm = utils.mult_matrix((1, 0, 0, 1, tx, ty), ts.Tm)
if len(word) > 0:
sentence.append(''.join(word))
verbose('current sentence becomes=', sentence)
word = []
verbose('current word becomes=', word)
self.paragraph.append(' '.join(sentence))
verbose('current paragraph becomes=', self.paragraph)
return
