fix: restore previous API

pdfminer/ascii85.py

@@ -0,0 +1,39 @@
+"""Python implementation of ASCII85/ASCIIHex decoder (Adobe version)."""
+
+import re
+from base64 import a85decode
+from binascii import unhexlify
+
+
+def ascii85decode(data: bytes) -> bytes:
+    """In ASCII85 encoding, every four bytes are encoded with five ASCII
+    letters, using 85 different types of characters (as 256**4 < 85**5).
+    When the length of the original bytes is not a multiple of 4, a special
+    rule is used for round up.
+
+    The Adobe's ASCII85 implementation is slightly different from
+    its original in handling the last characters.
+
+    """
+    return a85decode(data, adobe=True)
+
+
+bws_re = re.compile(rb"\s")
+
+
+def asciihexdecode(data: bytes) -> bytes:
+    """ASCIIHexDecode filter: PDFReference v1.4 section 3.3.1
+    For each pair of ASCII hexadecimal digits (0-9 and A-F or a-f), the
+    ASCIIHexDecode filter produces one byte of binary data. All white-space
+    characters are ignored. A right angle bracket character (>) indicates
+    EOD. Any other characters will cause an error. If the filter encounters
+    the EOD marker after reading an odd number of hexadecimal digits, it
+    will behave as if a 0 followed the last digit.
+    """
+    data = bws_re.sub(b"", data)
+    idx = data.find(b">")
+    if idx != -1:
+        data = data[:idx]
+        if idx % 2 == 1:
+            data += b"0"
+    return unhexlify(data)

pdfminer/pdftypes.py

@@ -1,9 +1,6 @@
 import io
 import logging
-import re
 import zlib
-from base64 import a85decode
-from binascii import unhexlify
 from typing import (
     TYPE_CHECKING,
     Any,
@@ -19,6 +16,7 @@
 from warnings import warn
 
 from pdfminer import pdfexceptions, settings
+from pdfminer.ascii85 import ascii85decode, asciihexdecode
 from pdfminer.ccitt import ccittfaxdecode
 from pdfminer.lzw import lzwdecode
 from pdfminer.psparser import LIT, PSObject
@@ -244,27 +242,6 @@ def decompress_corrupted(data: bytes) -> bytes:
     return result_str
 
 
-bws_re = re.compile(rb"\s")
-
-
-def asciihexdecode(data: bytes) -> bytes:
-    """ASCIIHexDecode filter: PDFReference v1.4 section 3.3.1
-    For each pair of ASCII hexadecimal digits (0-9 and A-F or a-f), the
-    ASCIIHexDecode filter produces one byte of binary data. All white-space
-    characters are ignored. A right angle bracket character (>) indicates
-    EOD. Any other characters will cause an error. If the filter encounters
-    the EOD marker after reading an odd number of hexadecimal digits, it
-    will behave as if a 0 followed the last digit.
-    """
-    data = bws_re.sub(b"", data)
-    idx = data.find(b">")
-    if idx != -1:
-        data = data[:idx]
-        if idx % 2 == 1:
-            data += b"0"
-    return unhexlify(data)
-
-
 class PDFStream(PDFObject):
     def __init__(
         self,
@@ -366,7 +343,7 @@ def decode(self) -> None:
             elif f in LITERALS_LZW_DECODE:
                 data = lzwdecode(data)
             elif f in LITERALS_ASCII85_DECODE:
-                data = a85decode(data, adobe=True)
+                data = ascii85decode(data)
             elif f in LITERALS_ASCIIHEX_DECODE:
                 data = asciihexdecode(data)
             elif f in LITERALS_RUNLENGTH_DECODE:

tests/test_pdfminer_crypto.py

@@ -1,11 +1,10 @@
 """Test of various compression/encoding modules (previously in doctests)"""
 
 import binascii
-from base64 import a85decode
 
 from pdfminer.arcfour import Arcfour
+from pdfminer.ascii85 import ascii85decode, asciihexdecode
 from pdfminer.lzw import lzwdecode
-from pdfminer.pdftypes import asciihexdecode
 from pdfminer.runlength import rldecode
 
 
@@ -19,13 +18,13 @@ def dehex(b):
     return binascii.unhexlify(b)
 
 
-class TestAsciiHex:
+class TestAscii85:
     def test_ascii85decode(self):
         """The sample string is taken from:
         http://en.wikipedia.org/w/index.php?title=Ascii85
         """
-        assert a85decode(b"9jqo^BlbD-BleB1DJ+*+F(f,q") == b"Man is distinguished"
-        assert a85decode(b"E,9)oF*2M7/c~>", adobe=True) == b"pleasure."
+        assert ascii85decode(b"9jqo^BlbD-BleB1DJ+*+F(f,q") == b"Man is distinguished"
+        assert ascii85decode(b"E,9)oF*2M7/c~>") == b"pleasure."
 
     def test_asciihexdecode(self):
         assert asciihexdecode(b"61 62 2e6364   65") == b"ab.cde"