Spaces:
Running
Running
File size: 8,700 Bytes
9b0f4a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 |
from typing import (
TYPE_CHECKING,
BinaryIO,
Iterable,
List,
Optional,
Sequence,
Union,
cast,
)
from pdf2zh import utils
from pdf2zh.pdfcolor import PDFColorSpace
from pdf2zh.pdffont import PDFFont, PDFUnicodeNotDefined
from pdf2zh.pdfpage import PDFPage
from pdf2zh.pdftypes import PDFStream
from pdf2zh.psparser import PSLiteral
from pdf2zh.utils import Matrix, PathSegment, Point, Rect
if TYPE_CHECKING:
from pdf2zh.pdfinterp import (
PDFGraphicState,
PDFResourceManager,
PDFStackT,
PDFTextState,
)
PDFTextSeq = Iterable[Union[int, float, bytes]]
class PDFDevice:
"""Translate the output of PDFPageInterpreter to the output that is needed"""
def __init__(self, rsrcmgr: "PDFResourceManager") -> None:
self.rsrcmgr = rsrcmgr
self.ctm: Optional[Matrix] = None
def __repr__(self) -> str:
return "<PDFDevice>"
def __enter__(self) -> "PDFDevice":
return self
def __exit__(self, exc_type: object, exc_val: object, exc_tb: object) -> None:
self.close()
def close(self) -> None:
pass
def set_ctm(self, ctm: Matrix) -> None:
self.ctm = ctm
def begin_tag(self, tag: PSLiteral, props: Optional["PDFStackT"] = None) -> None:
pass
def end_tag(self) -> None:
pass
def do_tag(self, tag: PSLiteral, props: Optional["PDFStackT"] = None) -> None:
pass
def begin_page(self, page: PDFPage, ctm: Matrix) -> None:
pass
def end_page(self, page: PDFPage) -> None:
pass
def begin_figure(self, name: str, bbox: Rect, matrix: Matrix) -> None:
pass
def end_figure(self, name: str) -> None:
pass
def paint_path(
self,
graphicstate: "PDFGraphicState",
stroke: bool,
fill: bool,
evenodd: bool,
path: Sequence[PathSegment],
) -> None:
pass
def render_image(self, name: str, stream: PDFStream) -> None:
pass
def render_string(
self,
textstate: "PDFTextState",
seq: PDFTextSeq,
ncs: PDFColorSpace,
graphicstate: "PDFGraphicState",
) -> None:
pass
class PDFTextDevice(PDFDevice):
def render_string(
self,
textstate: "PDFTextState",
seq: PDFTextSeq,
ncs: PDFColorSpace,
graphicstate: "PDFGraphicState",
) -> None:
assert self.ctm is not None
matrix = utils.mult_matrix(textstate.matrix, self.ctm)
font = textstate.font
fontsize = textstate.fontsize
scaling = textstate.scaling * 0.01
charspace = textstate.charspace * scaling
wordspace = textstate.wordspace * scaling
rise = textstate.rise
assert font is not None
if font.is_multibyte():
wordspace = 0
dxscale = 0.001 * fontsize * scaling
if font.is_vertical():
textstate.linematrix = self.render_string_vertical(
seq,
matrix,
textstate.linematrix,
font,
fontsize,
scaling,
charspace,
wordspace,
rise,
dxscale,
ncs,
graphicstate,
)
else:
textstate.linematrix = self.render_string_horizontal(
seq,
matrix,
textstate.linematrix,
font,
fontsize,
scaling,
charspace,
wordspace,
rise,
dxscale,
ncs,
graphicstate,
)
def render_string_horizontal(
self,
seq: PDFTextSeq,
matrix: Matrix,
pos: Point,
font: PDFFont,
fontsize: float,
scaling: float,
charspace: float,
wordspace: float,
rise: float,
dxscale: float,
ncs: PDFColorSpace,
graphicstate: "PDFGraphicState",
) -> Point:
(x, y) = pos
needcharspace = False
for obj in seq:
if isinstance(obj, (int, float)):
x -= obj * dxscale
needcharspace = True
else:
for cid in font.decode(obj):
if needcharspace:
x += charspace
x += self.render_char(
utils.translate_matrix(matrix, (x, y)),
font,
fontsize,
scaling,
rise,
cid,
ncs,
graphicstate,
)
if cid == 32 and wordspace:
x += wordspace
needcharspace = True
return (x, y)
def render_string_vertical(
self,
seq: PDFTextSeq,
matrix: Matrix,
pos: Point,
font: PDFFont,
fontsize: float,
scaling: float,
charspace: float,
wordspace: float,
rise: float,
dxscale: float,
ncs: PDFColorSpace,
graphicstate: "PDFGraphicState",
) -> Point:
(x, y) = pos
needcharspace = False
for obj in seq:
if isinstance(obj, (int, float)):
y -= obj * dxscale
needcharspace = True
else:
for cid in font.decode(obj):
if needcharspace:
y += charspace
y += self.render_char(
utils.translate_matrix(matrix, (x, y)),
font,
fontsize,
scaling,
rise,
cid,
ncs,
graphicstate,
)
if cid == 32 and wordspace:
y += wordspace
needcharspace = True
return (x, y)
def render_char(
self,
matrix: Matrix,
font: PDFFont,
fontsize: float,
scaling: float,
rise: float,
cid: int,
ncs: PDFColorSpace,
graphicstate: "PDFGraphicState",
) -> float:
return 0
class TagExtractor(PDFDevice):
def __init__(
self,
rsrcmgr: "PDFResourceManager",
outfp: BinaryIO,
codec: str = "utf-8",
) -> None:
PDFDevice.__init__(self, rsrcmgr)
self.outfp = outfp
self.codec = codec
self.pageno = 0
self._stack: List[PSLiteral] = []
def render_string(
self,
textstate: "PDFTextState",
seq: PDFTextSeq,
ncs: PDFColorSpace,
graphicstate: "PDFGraphicState",
) -> None:
font = textstate.font
assert font is not None
text = ""
for obj in seq:
if isinstance(obj, str):
obj = utils.make_compat_bytes(obj)
if not isinstance(obj, bytes):
continue
chars = font.decode(obj)
for cid in chars:
try:
char = font.to_unichr(cid)
text += char
except PDFUnicodeNotDefined:
pass
self._write(utils.enc(text))
def begin_page(self, page: PDFPage, ctm: Matrix) -> None:
output = '<page id="%s" bbox="%s" rotate="%d">' % (
self.pageno,
utils.bbox2str(page.mediabox),
page.rotate,
)
self._write(output)
def end_page(self, page: PDFPage) -> None:
self._write("</page>\n")
self.pageno += 1
def begin_tag(self, tag: PSLiteral, props: Optional["PDFStackT"] = None) -> None:
s = ""
if isinstance(props, dict):
s = "".join(
[
f' {utils.enc(k)}="{utils.make_compat_str(v)}"'
for (k, v) in sorted(props.items())
],
)
out_s = f"<{utils.enc(cast(str, tag.name))}{s}>"
self._write(out_s)
self._stack.append(tag)
def end_tag(self) -> None:
assert self._stack, str(self.pageno)
tag = self._stack.pop(-1)
out_s = "</%s>" % utils.enc(cast(str, tag.name))
self._write(out_s)
def do_tag(self, tag: PSLiteral, props: Optional["PDFStackT"] = None) -> None:
self.begin_tag(tag, props)
self._stack.pop(-1)
def _write(self, s: str) -> None:
self.outfp.write(s.encode(self.codec))
|