Changeset 702

Timestamp:

01/24/06 13:30:47 (3 years ago)

Author:

laotzu

Message:

Add ASCII85 decode

Files:

• pypdf/trunk/pyPdf/filters.py (modified) (2 diffs)

pypdf/trunk/pyPdf/filters.py

@@ -97 +97 @@
-    decode = staticmethod(decode)
-
+class ASCII85Decode(object):
+    def decode(data, decodeParms=None):
+        retval = ""
+        group = []
+        x = 0
+        hitEod = False
+        while not hitEod:
+            c = data[x]
+            if len(retval) == 0 and c == "<" and data[x+1] == "~":
+                x += 2
+                continue
+            elif c.isspace():
+                x += 1
+                continue
+            elif c == 'z':
+                assert len(group) == 0
+                retval += '\x00\x00\x00\x00'
+                continue
+            elif c == "~" and data[x+1] == ">":
+                if len(group) != 0:
+                    # cannot have a final group of just 1 char
+                    assert len(group) > 1
+                    cnt = len(group) - 1
+                    group += [ 85, 85, 85 ]
+                    hitEod = cnt
+                else:
+                    break
+            else:
+                c = ord(c) - 33
+                assert c >= 0 and c < 85
+                group += [ c ]
+            if len(group) >= 5:
+                b = group[0] * (85**4) + \
+                    group[1] * (85**3) + \
+                    group[2] * (85**2) + \
+                    group[3] * 85 + \
+                    group[4]
+                assert b < (2**32 - 1)
+                c4 = chr((b >> 0) % 256)
+                c3 = chr((b >> 8) % 256)
+                c2 = chr((b >> 16) % 256)
+                c1 = chr(b >> 24)
+                retval += (c1 + c2 + c3 + c4)
+                if hitEod:
+                    retval = retval[:-4+hitEod]
+                group = []
+            x += 1
+        return retval
+    decode = staticmethod(decode)
+
-def decodeStreamData(stream):
-    filters = stream.get("/Filter", ())
@@ -115 +165 @@
-if __name__ == "__main__":
-    assert "abc" == ASCIIHexDecode.decode('61\n626\n3>')
+
+    ascii85Test = """
+     <~9jqo^BlbD-BleB1DJ+*+F(f,q/0JhKF<GL>Cj@.4Gp$d7F!,L7@<6@)/0JDEF<G%<+EV:2F!,
+     O<DJ+*.@<*K0@<6L(Df-\\0Ec5e;DffZ(EZee.Bl.9pF"AGXBPCsi+DGm>@3BB/F*&OCAfu2/AKY
+     i(DIb:@FD,*)+C]U=@3BN#EcYf8ATD3s@q?d$AftVqCh[NqF<G:8+EV:.+Cf>-FD5W8ARlolDIa
+     l(DId<j@<?3r@:F%a+D58'ATD4$Bl@l3De:,-DJs`8ARoFb/0JMK@qB4^F!,R<AKZ&-DfTqBG%G
+     >uD.RTpAKYo'+CT/5+Cei#DII?(E,9)oF*2M7/c~>
+    """
+    ascii85_originalText="Man is distinguished, not only by his reason, but by this singular passion from other animals, which is a lust of the mind, that by a perseverance of delight in the continued and indefatigable generation of knowledge, exceeds the short vehemence of any carnal pleasure."
+    assert ASCII85Decode.decode(ascii85Test) == ascii85_originalText