pdftypes.py 7.94 KB
Newer Older
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
#!/usr/bin/env python
import sys
import zlib
from lzw import lzwdecode
from ascii85 import ascii85decode, asciihexdecode
from runlength import rldecode
from psparser import PSException, PSObject
from psparser import LIT, KWD, STRICT

LITERAL_CRYPT = LIT('Crypt')

# Abbreviation of Filter names in PDF 4.8.6. "Inline Images"
LITERALS_FLATE_DECODE = (LIT('FlateDecode'), LIT('Fl'))
LITERALS_LZW_DECODE = (LIT('LZWDecode'), LIT('LZW'))
LITERALS_ASCII85_DECODE = (LIT('ASCII85Decode'), LIT('A85'))
LITERALS_ASCIIHEX_DECODE = (LIT('ASCIIHexDecode'), LIT('AHx'))
LITERALS_RUNLENGTH_DECODE = (LIT('RunLengthDecode'), LIT('RL'))
LITERALS_CCITTFAX_DECODE = (LIT('CCITTFaxDecode'), LIT('CCF'))
LITERALS_DCT_DECODE = (LIT('DCTDecode'), LIT('DCT'))


##  PDF Objects
##
class PDFObject(PSObject): pass

class PDFException(PSException): pass
class PDFTypeError(PDFException): pass
class PDFValueError(PDFException): pass
class PDFNotImplementedError(PSException): pass


##  PDFObjRef
##
class PDFObjRef(PDFObject):

    def __init__(self, doc, objid, _):
        if objid == 0:
            if STRICT:
                raise PDFValueError('PDF object id cannot be 0.')
        self.doc = doc
        self.objid = objid
        #self.genno = genno  # Never used.
        return

    def __repr__(self):
        return '<PDFObjRef:%d>' % (self.objid)

    def resolve(self):
        return self.doc.getobj(self.objid)


# resolve
def resolve1(x):
    '''
    Resolve an object. If this is an array or dictionary,
    it may still contains some indirect objects inside.
    '''
    while isinstance(x, PDFObjRef):
        x = x.resolve()
    return x

def resolve_all(x):
    '''
    Recursively resolve X and all the internals.
    Make sure there is no indirect reference within the nested object.
    This procedure might be slow.
    '''
    while isinstance(x, PDFObjRef):
        x = x.resolve()
    if isinstance(x, list):
        x = [ resolve_all(v) for v in x ]
    elif isinstance(x, dict):
        for (k,v) in x.iteritems():
            x[k] = resolve_all(v)
    return x

def decipher_all(decipher, objid, genno, x):
    '''
    Recursively decipher X.
    '''
    if isinstance(x, str):
        return decipher(objid, genno, x)
    if isinstance(x, list):
        x = [ decipher_all(decipher, objid, genno, v) for v in x ]
    elif isinstance(x, dict):
        for (k,v) in x.iteritems():
            x[k] = decipher_all(decipher, objid, genno, v)
    return x

# Type cheking
def int_value(x):
    x = resolve1(x)
    if not isinstance(x, int):
        if STRICT:
            raise PDFTypeError('Integer required: %r' % x)
        return 0
    return x

def float_value(x):
    x = resolve1(x)
    if not isinstance(x, float):
        if STRICT:
            raise PDFTypeError('Float required: %r' % x)
        return 0.0
    return x

def num_value(x):
    x = resolve1(x)
    if not (isinstance(x, int) or isinstance(x, float)):
        if STRICT:
            raise PDFTypeError('Int or Float required: %r' % x)
        return 0
    return x

def str_value(x):
    x = resolve1(x)
    if not isinstance(x, str):
        if STRICT:
            raise PDFTypeError('String required: %r' % x)
        return ''
    return x

def list_value(x):
    x = resolve1(x)
    if not (isinstance(x, list) or isinstance(x, tuple)):
        if STRICT:
            raise PDFTypeError('List required: %r' % x)
        return []
    return x

def dict_value(x):
    x = resolve1(x)
    if not isinstance(x, dict):
        if STRICT:
            raise PDFTypeError('Dict required: %r' % x)
        return {}
    return x

def stream_value(x):
    x = resolve1(x)
    if not isinstance(x, PDFStream):
        if STRICT:
            raise PDFTypeError('PDFStream required: %r' % x)
        return PDFStream({}, '')
    return x


##  PDFStream type
##
class PDFStream(PDFObject):

    def __init__(self, attrs, rawdata, decipher=None):
        assert isinstance(attrs, dict)
        self.attrs = attrs
        self.rawdata = rawdata
        self.decipher = decipher
        self.data = None
        self.objid = None
        self.genno = None
        return

    def set_objid(self, objid, genno):
        self.objid = objid
        self.genno = genno
        return

    def __repr__(self):
        if self.data is None:
            assert self.rawdata is not None
            return '<PDFStream(%r): raw=%d, %r>' % (self.objid, len(self.rawdata), self.attrs)
        else:
            assert self.data is not None
            return '<PDFStream(%r): len=%d, %r>' % (self.objid, len(self.data), self.attrs)

    def __contains__(self, name):
        return name in self.attrs
    
    def __getitem__(self, name):
        return self.attrs[name]
    
    def get(self, name, default=None):
        return self.attrs.get(name, default)
    
    def get_any(self, names, default=None):
        for name in names:
            if name in self.attrs:
                return self.attrs[name]
        return default

    def get_filters(self):
        filters = self.get_any(('F', 'Filter'))
        if not filters: return []
        if isinstance(filters, list): return filters
        return [ filters ]

    def decomp(self,data):
        buf = data
        # some FlateDecode streams have garbage (newlines, etc) appended to the
        # end.  remove chars from the end to try and decompress the buffer
        while 8 <= len(buf):
            try:
                # will get errors if the document is encrypted.
                dco = zlib.decompressobj()
                return dco.decompress(buf)
            except zlib.error:
                buf = buf[:-1]
        raise Exception, "zlib.error while decompressing data"

    def decode(self):
        assert self.data is None and self.rawdata != None
        data = self.rawdata
        if self.decipher:
            # Handle encryption
            data = self.decipher(self.objid, self.genno, data)
        filters = self.get_filters()
        if not filters:
            self.data = data
            self.rawdata = None
            return
        for f in filters:
            if f in LITERALS_FLATE_DECODE:
                # will get errors if the document is encrypted.
                data = self.decomp(data)
            elif f in LITERALS_LZW_DECODE:
                data = lzwdecode(data)
            elif f in LITERALS_ASCII85_DECODE:
                data = ascii85decode(data)
            elif f in LITERALS_ASCIIHEX_DECODE:
                data = asciihexdecode(data)
            elif f in LITERALS_RUNLENGTH_DECODE:
                data = rldecode(data)
            elif f in LITERALS_CCITTFAX_DECODE:
                #data = ccittfaxdecode(data)
                raise PDFNotImplementedError('Unsupported filter: %r' % f)
            elif f == LITERAL_CRYPT:
                # not yet..
                raise PDFNotImplementedError('/Crypt filter is unsupported')
            else:
                raise PDFNotImplementedError('Unsupported filter: %r' % f)
            # apply predictors
            params = self.get_any(('DP', 'DecodeParms', 'FDecodeParms'), {})
            if 'Predictor' in params and 'Columns' in params:
                pred = int_value(params['Predictor'])
                columns = int_value(params['Columns'])
                if pred:
                    if pred != 12:
                        raise PDFNotImplementedError('Unsupported predictor: %r' % pred)
                    buf = ''
                    ent0 = '\x00' * columns
                    for i in xrange(0, len(data), columns+1):
                        pred = data[i]
                        ent1 = data[i+1:i+1+columns]
                        if pred == '\x02':
                            ent1 = ''.join( chr((ord(a)+ord(b)) & 255) for (a,b) in zip(ent0,ent1) )
                        buf += ent1
                        ent0 = ent1
                    data = buf
        self.data = data
        self.rawdata = None
        return

    def get_data(self):
        if self.data is None:
            self.decode()
        return self.data

    def get_rawdata(self):
        return self.rawdata