aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/python/Pillow/py3/PIL/EpsImagePlugin.py
blob: d2e60aa0759223c427189a662d6006aeafc4a584 (plain) (blame)
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
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
#
# The Python Imaging Library.
# $Id$
#
# EPS file handling
#
# History:
# 1995-09-01 fl   Created (0.1)
# 1996-05-18 fl   Don't choke on "atend" fields, Ghostscript interface (0.2)
# 1996-08-22 fl   Don't choke on floating point BoundingBox values
# 1996-08-23 fl   Handle files from Macintosh (0.3)
# 2001-02-17 fl   Use 're' instead of 'regex' (Python 2.1) (0.4)
# 2003-09-07 fl   Check gs.close status (from Federico Di Gregorio) (0.5)
# 2014-05-07 e    Handling of EPS with binary preview and fixed resolution
#                 resizing
#
# Copyright (c) 1997-2003 by Secret Labs AB.
# Copyright (c) 1995-2003 by Fredrik Lundh
#
# See the README file for information on usage and redistribution.
#
from __future__ import annotations

import io
import os
import re
import subprocess
import sys
import tempfile

from . import Image, ImageFile
from ._binary import i32le as i32
from ._deprecate import deprecate

# --------------------------------------------------------------------


split = re.compile(r"^%%([^:]*):[ \t]*(.*)[ \t]*$")
field = re.compile(r"^%[%!\w]([^:]*)[ \t]*$")

gs_binary = None
gs_windows_binary = None


def has_ghostscript():
    global gs_binary, gs_windows_binary
    if gs_binary is None:
        if sys.platform.startswith("win"):
            if gs_windows_binary is None:
                import shutil

                for binary in ("gswin32c", "gswin64c", "gs"):
                    if shutil.which(binary) is not None:
                        gs_windows_binary = binary
                        break
                else:
                    gs_windows_binary = False
            gs_binary = gs_windows_binary
        else:
            try:
                subprocess.check_call(["gs", "--version"], stdout=subprocess.DEVNULL)
                gs_binary = "gs"
            except OSError:
                gs_binary = False
    return gs_binary is not False


def Ghostscript(tile, size, fp, scale=1, transparency=False):
    """Render an image using Ghostscript"""
    global gs_binary
    if not has_ghostscript():
        msg = "Unable to locate Ghostscript on paths"
        raise OSError(msg)

    # Unpack decoder tile
    decoder, tile, offset, data = tile[0]
    length, bbox = data

    # Hack to support hi-res rendering
    scale = int(scale) or 1
    width = size[0] * scale
    height = size[1] * scale
    # resolution is dependent on bbox and size
    res_x = 72.0 * width / (bbox[2] - bbox[0])
    res_y = 72.0 * height / (bbox[3] - bbox[1])

    out_fd, outfile = tempfile.mkstemp()
    os.close(out_fd)

    infile_temp = None
    if hasattr(fp, "name") and os.path.exists(fp.name):
        infile = fp.name
    else:
        in_fd, infile_temp = tempfile.mkstemp()
        os.close(in_fd)
        infile = infile_temp

        # Ignore length and offset!
        # Ghostscript can read it
        # Copy whole file to read in Ghostscript
        with open(infile_temp, "wb") as f:
            # fetch length of fp
            fp.seek(0, io.SEEK_END)
            fsize = fp.tell()
            # ensure start position
            # go back
            fp.seek(0)
            lengthfile = fsize
            while lengthfile > 0:
                s = fp.read(min(lengthfile, 100 * 1024))
                if not s:
                    break
                lengthfile -= len(s)
                f.write(s)

    device = "pngalpha" if transparency else "ppmraw"

    # Build Ghostscript command
    command = [
        gs_binary,
        "-q",  # quiet mode
        f"-g{width:d}x{height:d}",  # set output geometry (pixels)
        f"-r{res_x:f}x{res_y:f}",  # set input DPI (dots per inch)
        "-dBATCH",  # exit after processing
        "-dNOPAUSE",  # don't pause between pages
        "-dSAFER",  # safe mode
        f"-sDEVICE={device}",
        f"-sOutputFile={outfile}",  # output file
        # adjust for image origin
        "-c",
        f"{-bbox[0]} {-bbox[1]} translate",
        "-f",
        infile,  # input file
        # showpage (see https://bugs.ghostscript.com/show_bug.cgi?id=698272)
        "-c",
        "showpage",
    ]

    # push data through Ghostscript
    try:
        startupinfo = None
        if sys.platform.startswith("win"):
            startupinfo = subprocess.STARTUPINFO()
            startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
        subprocess.check_call(command, startupinfo=startupinfo)
        out_im = Image.open(outfile)
        out_im.load()
    finally:
        try:
            os.unlink(outfile)
            if infile_temp:
                os.unlink(infile_temp)
        except OSError:
            pass

    im = out_im.im.copy()
    out_im.close()
    return im


class PSFile:
    """
    Wrapper for bytesio object that treats either CR or LF as end of line.
    This class is no longer used internally, but kept for backwards compatibility.
    """

    def __init__(self, fp):
        deprecate(
            "PSFile",
            11,
            action="If you need the functionality of this class "
            "you will need to implement it yourself.",
        )
        self.fp = fp
        self.char = None

    def seek(self, offset, whence=io.SEEK_SET):
        self.char = None
        self.fp.seek(offset, whence)

    def readline(self):
        s = [self.char or b""]
        self.char = None

        c = self.fp.read(1)
        while (c not in b"\r\n") and len(c):
            s.append(c)
            c = self.fp.read(1)

        self.char = self.fp.read(1)
        # line endings can be 1 or 2 of \r \n, in either order
        if self.char in b"\r\n":
            self.char = None

        return b"".join(s).decode("latin-1")


def _accept(prefix):
    return prefix[:4] == b"%!PS" or (len(prefix) >= 4 and i32(prefix) == 0xC6D3D0C5)


##
# Image plugin for Encapsulated PostScript. This plugin supports only
# a few variants of this format.


class EpsImageFile(ImageFile.ImageFile):
    """EPS File Parser for the Python Imaging Library"""

    format = "EPS"
    format_description = "Encapsulated Postscript"

    mode_map = {1: "L", 2: "LAB", 3: "RGB", 4: "CMYK"}

    def _open(self):
        (length, offset) = self._find_offset(self.fp)

        # go to offset - start of "%!PS"
        self.fp.seek(offset)

        self._mode = "RGB"
        self._size = None

        byte_arr = bytearray(255)
        bytes_mv = memoryview(byte_arr)
        bytes_read = 0
        reading_header_comments = True
        reading_trailer_comments = False
        trailer_reached = False

        def check_required_header_comments():
            if "PS-Adobe" not in self.info:
                msg = 'EPS header missing "%!PS-Adobe" comment'
                raise SyntaxError(msg)
            if "BoundingBox" not in self.info:
                msg = 'EPS header missing "%%BoundingBox" comment'
                raise SyntaxError(msg)

        def _read_comment(s):
            nonlocal reading_trailer_comments
            try:
                m = split.match(s)
            except re.error as e:
                msg = "not an EPS file"
                raise SyntaxError(msg) from e

            if m:
                k, v = m.group(1, 2)
                self.info[k] = v
                if k == "BoundingBox":
                    if v == "(atend)":
                        reading_trailer_comments = True
                    elif not self._size or (
                        trailer_reached and reading_trailer_comments
                    ):
                        try:
                            # Note: The DSC spec says that BoundingBox
                            # fields should be integers, but some drivers
                            # put floating point values there anyway.
                            box = [int(float(i)) for i in v.split()]
                            self._size = box[2] - box[0], box[3] - box[1]
                            self.tile = [
                                ("eps", (0, 0) + self.size, offset, (length, box))
                            ]
                        except Exception:
                            pass
                return True

        while True:
            byte = self.fp.read(1)
            if byte == b"":
                # if we didn't read a byte we must be at the end of the file
                if bytes_read == 0:
                    break
            elif byte in b"\r\n":
                # if we read a line ending character, ignore it and parse what
                # we have already read. if we haven't read any other characters,
                # continue reading
                if bytes_read == 0:
                    continue
            else:
                # ASCII/hexadecimal lines in an EPS file must not exceed
                # 255 characters, not including line ending characters
                if bytes_read >= 255:
                    # only enforce this for lines starting with a "%",
                    # otherwise assume it's binary data
                    if byte_arr[0] == ord("%"):
                        msg = "not an EPS file"
                        raise SyntaxError(msg)
                    else:
                        if reading_header_comments:
                            check_required_header_comments()
                            reading_header_comments = False
                        # reset bytes_read so we can keep reading
                        # data until the end of the line
                        bytes_read = 0
                byte_arr[bytes_read] = byte[0]
                bytes_read += 1
                continue

            if reading_header_comments:
                # Load EPS header

                # if this line doesn't start with a "%",
                # or does start with "%%EndComments",
                # then we've reached the end of the header/comments
                if byte_arr[0] != ord("%") or bytes_mv[:13] == b"%%EndComments":
                    check_required_header_comments()
                    reading_header_comments = False
                    continue

                s = str(bytes_mv[:bytes_read], "latin-1")
                if not _read_comment(s):
                    m = field.match(s)
                    if m:
                        k = m.group(1)
                        if k[:8] == "PS-Adobe":
                            self.info["PS-Adobe"] = k[9:]
                        else:
                            self.info[k] = ""
                    elif s[0] == "%":
                        # handle non-DSC PostScript comments that some
                        # tools mistakenly put in the Comments section
                        pass
                    else:
                        msg = "bad EPS header"
                        raise OSError(msg)
            elif bytes_mv[:11] == b"%ImageData:":
                # Check for an "ImageData" descriptor
                # https://www.adobe.com/devnet-apps/photoshop/fileformatashtml/#50577413_pgfId-1035096

                # Values:
                # columns
                # rows
                # bit depth (1 or 8)
                # mode (1: L, 2: LAB, 3: RGB, 4: CMYK)
                # number of padding channels
                # block size (number of bytes per row per channel)
                # binary/ascii (1: binary, 2: ascii)
                # data start identifier (the image data follows after a single line
                #   consisting only of this quoted value)
                image_data_values = byte_arr[11:bytes_read].split(None, 7)
                columns, rows, bit_depth, mode_id = (
                    int(value) for value in image_data_values[:4]
                )

                if bit_depth == 1:
                    self._mode = "1"
                elif bit_depth == 8:
                    try:
                        self._mode = self.mode_map[mode_id]
                    except ValueError:
                        break
                else:
                    break

                self._size = columns, rows
                return
            elif trailer_reached and reading_trailer_comments:
                # Load EPS trailer

                # if this line starts with "%%EOF",
                # then we've reached the end of the file
                if bytes_mv[:5] == b"%%EOF":
                    break

                s = str(bytes_mv[:bytes_read], "latin-1")
                _read_comment(s)
            elif bytes_mv[:9] == b"%%Trailer":
                trailer_reached = True
            bytes_read = 0

        check_required_header_comments()

        if not self._size:
            msg = "cannot determine EPS bounding box"
            raise OSError(msg)

    def _find_offset(self, fp):
        s = fp.read(4)

        if s == b"%!PS":
            # for HEAD without binary preview
            fp.seek(0, io.SEEK_END)
            length = fp.tell()
            offset = 0
        elif i32(s) == 0xC6D3D0C5:
            # FIX for: Some EPS file not handled correctly / issue #302
            # EPS can contain binary data
            # or start directly with latin coding
            # more info see:
            # https://web.archive.org/web/20160528181353/http://partners.adobe.com/public/developer/en/ps/5002.EPSF_Spec.pdf
            s = fp.read(8)
            offset = i32(s)
            length = i32(s, 4)
        else:
            msg = "not an EPS file"
            raise SyntaxError(msg)

        return length, offset

    def load(self, scale=1, transparency=False):
        # Load EPS via Ghostscript
        if self.tile:
            self.im = Ghostscript(self.tile, self.size, self.fp, scale, transparency)
            self._mode = self.im.mode
            self._size = self.im.size
            self.tile = []
        return Image.Image.load(self)

    def load_seek(self, *args, **kwargs):
        # we can't incrementally load, so force ImageFile.parser to
        # use our custom load method by defining this method.
        pass


# --------------------------------------------------------------------


def _save(im, fp, filename, eps=1):
    """EPS Writer for the Python Imaging Library."""

    # make sure image data is available
    im.load()

    # determine PostScript image mode
    if im.mode == "L":
        operator = (8, 1, b"image")
    elif im.mode == "RGB":
        operator = (8, 3, b"false 3 colorimage")
    elif im.mode == "CMYK":
        operator = (8, 4, b"false 4 colorimage")
    else:
        msg = "image mode is not supported"
        raise ValueError(msg)

    if eps:
        # write EPS header
        fp.write(b"%!PS-Adobe-3.0 EPSF-3.0\n")
        fp.write(b"%%Creator: PIL 0.1 EpsEncode\n")
        # fp.write("%%CreationDate: %s"...)
        fp.write(b"%%%%BoundingBox: 0 0 %d %d\n" % im.size)
        fp.write(b"%%Pages: 1\n")
        fp.write(b"%%EndComments\n")
        fp.write(b"%%Page: 1 1\n")
        fp.write(b"%%ImageData: %d %d " % im.size)
        fp.write(b'%d %d 0 1 1 "%s"\n' % operator)

    # image header
    fp.write(b"gsave\n")
    fp.write(b"10 dict begin\n")
    fp.write(b"/buf %d string def\n" % (im.size[0] * operator[1]))
    fp.write(b"%d %d scale\n" % im.size)
    fp.write(b"%d %d 8\n" % im.size)  # <= bits
    fp.write(b"[%d 0 0 -%d 0 %d]\n" % (im.size[0], im.size[1], im.size[1]))
    fp.write(b"{ currentfile buf readhexstring pop } bind\n")
    fp.write(operator[2] + b"\n")
    if hasattr(fp, "flush"):
        fp.flush()

    ImageFile._save(im, fp, [("eps", (0, 0) + im.size, 0, None)])

    fp.write(b"\n%%%%EndBinary\n")
    fp.write(b"grestore end\n")
    if hasattr(fp, "flush"):
        fp.flush()


# --------------------------------------------------------------------


Image.register_open(EpsImageFile.format, EpsImageFile, _accept)

Image.register_save(EpsImageFile.format, _save)

Image.register_extensions(EpsImageFile.format, [".ps", ".eps"])

Image.register_mime(EpsImageFile.format, "application/postscript")