class TextPositionTracker(PDFLayoutAnalyzer):
"""A page layout analyzer that pays attention to text visibility"""
def __init__(self, rsrcmgr, pageno=1, laparams=None):
super().__init__(rsrcmgr, pageno, laparams)
self.textstate = None
self.result = None
self.cur_item = None # not defined in pdfminer code as it should be
def begin_page(self, page, ctm):
super().begin_page(page, ctm)
self.cur_item = LTPage(self.pageno, page.mediabox)
def end_page(self, page):
assert not self._stack, str(len(self._stack))
assert isinstance(self.cur_item, LTPage), str(type(self.cur_item))
if self.laparams is not None:
self.cur_item.analyze(self.laparams)
self.pageno += 1
self.receive_layout(self.cur_item)
def render_string(self, textstate, seq, ncs, graphicstate):
self.textstate = textstate.copy()
super().render_string(self.textstate, seq, ncs, graphicstate)
def render_char(
self, matrix, font, fontsize, scaling, rise, cid, ncs, graphicstate
):
try:
text = font.to_unichr(cid)
assert isinstance(text, str), str(type(text))
except PDFUnicodeNotDefined:
text = self.handle_undefined_char(font, cid)
textwidth = font.char_width(cid)
textdisp = font.char_disp(cid)
item = LTStateAwareChar(
matrix,
font,
fontsize,
scaling,
rise,
text,
textwidth,
textdisp,
ncs,
graphicstate,
self.textstate,
)
self.cur_item.add(item)
return item.adv
def handle_undefined_char(self, font, cid):
# log.info('undefined: %r, %r', font, cid)
return (font.fontname, cid)
def receive_layout(self, ltpage):
self.result = ltpage
def get_result(self):
return self.result
def begin_page(self, page, ctm):
(x0, y0, x1, y1) = page.mediabox
(x0, y0) = apply_matrix_pt(ctm, (x0, y0))
(x1, y1) = apply_matrix_pt(ctm, (x1, y1))
mediabox = (0, 0, abs(x0-x1), abs(y0-y1))
self.cur_item = LTPage(self.pageno, mediabox)
return
def begin_page(self, page, ctm):
super().begin_page(page, ctm)
self.cur_item = LTPage(self.pageno, page.mediabox)
def begin_page(self, page): self.cur_item = LTPage(self.pageno, page.mediabox, page.rotate) return
def __init__(self, pageid, bbox, rotate=0):
LTPage.__init__(self, pageid, bbox)
return