/usr/lib/ruby/vendor_ruby/pdf/reader/buffer.rb is in ruby-pdf-reader 1.3.3-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | # coding: ASCII-8BIT
################################################################################
#
# Copyright (C) 2010 James Healy (jimmy@deefa.com)
#
# Permission is hereby granted, free of charge, to any person obtaining
# a copy of this software and associated documentation files (the
# "Software"), to deal in the Software without restriction, including
# without limitation the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so, subject to
# the following conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#
################################################################################
class PDF::Reader
# A string tokeniser that recognises PDF grammar. When passed an IO stream or a
# string, repeated calls to token() will return the next token from the source.
#
# This is very low level, and getting the raw tokens is not very useful in itself.
#
# This will usually be used in conjunction with PDF:Reader::Parser, which converts
# the raw tokens into objects we can work with (strings, ints, arrays, etc)
#
class Buffer
TOKEN_WHITESPACE=[0x00, 0x09, 0x0A, 0x0C, 0x0D, 0x20]
# some strings for comparissons. Declaring them here avoids creating new
# strings that need GC over and over
LEFT_PAREN = "("
LESS_THAN = "<"
STREAM = "stream"
ID = "ID"
FWD_SLASH = "/"
attr_reader :pos
# Creates a new buffer.
#
# Params:
#
# io - an IO stream or string with the raw data to tokenise
#
# options:
#
# :seek - a byte offset to seek to before starting to tokenise
# :content_stream - set to true if buffer will be tokenising a
# content stream. Defaults to false
#
def initialize (io, opts = {})
@io = io
@tokens = []
@in_content_stream = opts[:content_stream]
@io.seek(opts[:seek]) if opts[:seek]
@pos = @io.pos
end
# return true if there are no more tokens left
#
def empty?
prepare_tokens if @tokens.size < 3
@tokens.empty?
end
# return raw bytes from the underlying IO stream.
#
# bytes - the number of bytes to read
#
# options:
#
# :skip_eol - if true, the IO stream is advanced past a CRLF or LF that
# is sitting under the io cursor.
#
def read(bytes, opts = {})
reset_pos
if opts[:skip_eol]
@io.seek(-1, IO::SEEK_CUR)
str = @io.read(2)
if str.nil?
return nil
elsif str == "\r\n"
# do nothing
elsif str[0,1] == "\n"
@io.seek(-1, IO::SEEK_CUR)
else
@io.seek(-2, IO::SEEK_CUR)
end
end
bytes = @io.read(bytes)
save_pos
bytes
end
# return the next token from the source. Returns a string if a token
# is found, nil if there are no tokens left.
#
def token
reset_pos
prepare_tokens if @tokens.size < 3
merge_indirect_reference
prepare_tokens if @tokens.size < 3
@tokens.shift
end
# return the byte offset where the first XRef table in th source can be found.
#
def find_first_xref_offset
check_size_is_non_zero
@io.seek(-1024, IO::SEEK_END) rescue @io.seek(0)
data = @io.read(1024)
# the PDF 1.7 spec (section #3.4) says that EOL markers can be either \r, \n, or both.
lines = data.split(/[\n\r]+/).reverse
eof_index = lines.index { |l| l.strip[/^%%EOF/] }
raise MalformedPDFError, "PDF does not contain EOF marker" if eof_index.nil?
raise MalformedPDFError, "PDF EOF marker does not follow offset" if eof_index >= lines.size-1
lines[eof_index+1].to_i
end
private
def check_size_is_non_zero
@io.seek(-1, IO::SEEK_END)
@io.seek(0)
rescue Errno::EINVAL
raise MalformedPDFError, "PDF file is empty"
end
# Returns true if this buffer is parsing a content stream
#
def in_content_stream?
@in_content_stream ? true : false
end
# Some bastard moved our IO stream cursor. Restore it.
#
def reset_pos
@io.seek(@pos) if @io.pos != @pos
end
# save the current position of the source IO stream. If someone else (like another buffer)
# moves the cursor, we can then restore it.
#
def save_pos
@pos = @io.pos
end
# attempt to prime the buffer with the next few tokens.
#
def prepare_tokens
10.times do
case state
when :literal_string then prepare_literal_token
when :hex_string then prepare_hex_token
when :regular then prepare_regular_token
when :inline then prepare_inline_token
end
end
save_pos
end
# tokenising behaves slightly differently based on the current context.
# Determine the current context/state by examining the last token we found
#
def state
case @tokens.last
when LEFT_PAREN then :literal_string
when LESS_THAN then :hex_string
when STREAM then :stream
when ID
if in_content_stream? && @tokens[-2] != FWD_SLASH
:inline
else
:regular
end
else
:regular
end
end
# detect a series of 3 tokens that make up an indirect object. If we find
# them, replace the tokens with a PDF::Reader::Reference instance.
#
# Merging them into a single string was another option, but that would mean
# code further up the stack would need to check every token to see if it looks
# like an indirect object. For optimisation reasons, I'd rather avoid
# that extra check.
#
# It's incredibly likely that the next 3 tokens in the buffer are NOT an
# indirect reference, so test for that case first and avoid the relatively
# expensive regexp checks if possible.
#
def merge_indirect_reference
return if @tokens.size < 3
return if @tokens[2] != "R"
if @tokens[0].match(/\d+/) && @tokens[1].match(/\d+/)
@tokens[0] = PDF::Reader::Reference.new(@tokens[0].to_i, @tokens[1].to_i)
@tokens[1] = nil
@tokens[2] = nil
@tokens.compact!
end
end
def prepare_inline_token
str = ""
buffer = []
until buffer[0] =~ /\s/ && buffer[1, 2] == ["E", "I"]
chr = @io.read(1)
buffer << chr
if buffer.length > 3
str << buffer.shift
end
end
@tokens << string_token(str.strip)
@io.seek(-3, IO::SEEK_CUR) unless chr.nil?
end
# if we're currently inside a hex string, read hex nibbles until
# we find a closing >
#
def prepare_hex_token
str = ""
finished = false
while !finished
byte = @io.getbyte
if byte.nil?
finished = true # unbalanced params
elsif (48..57).include?(byte) || (65..90).include?(byte) || (97..122).include?(byte)
str << byte
elsif byte <= 32
# ignore it
else
@tokens << str if str.size > 0
@tokens << ">" if byte != 0x3E # '>'
@tokens << byte.chr
finished = true
end
end
end
# if we're currently inside a literal string we more or less just read bytes until
# we find the closing ) delimiter. Lots of bytes that would otherwise indicate the
# start of a new token in regular mode are left untouched when inside a literal
# string.
#
# The entire literal string will be returned as a single token. It will need further
# processing to fix things like escaped new lines, but that's someone else's
# problem.
#
def prepare_literal_token
str = ""
count = 1
while count > 0
byte = @io.getbyte
if byte.nil?
count = 0 # unbalanced params
elsif byte == 0x5C
str << byte << @io.getbyte
elsif byte == 0x28 # "("
str << "("
count += 1
elsif byte == 0x29 # ")"
count -= 1
str << ")" unless count == 0
else
str << byte unless count == 0
end
end
@tokens << str if str.size > 0
@tokens << ")"
end
# Extract the next regular token and stock it in our buffer, ready to be returned.
#
# What each byte means is complex, check out section "3.1.1 Character Set" of the 1.7 spec
# to read up on it.
#
def prepare_regular_token
tok = ""
while byte = @io.getbyte
case byte
when 0x25
# comment, ignore everything until the next EOL char
done = false
while !done
byte = @io.getbyte
done = true if byte.nil? || byte == 0x0A || byte == 0x0D
end
when *TOKEN_WHITESPACE
# white space, token finished
@tokens << tok if tok.size > 0
#If the token was empty, chomp the rest of the whitespace too
while TOKEN_WHITESPACE.include?(peek_byte) && tok.size == 0
@io.getbyte
end
tok = ""
break
when 0x3C
# opening delimiter '<', start of new token
@tokens << tok if tok.size > 0
if peek_byte == 0x3C # check if token is actually '<<'
@io.getbyte
@tokens << "<<"
else
@tokens << "<"
end
tok = ""
break
when 0x3E
# closing delimiter '>', start of new token
@tokens << tok if tok.size > 0
if peek_byte == 0x3E # check if token is actually '>>'
@io.getbyte
@tokens << ">>"
else
@tokens << ">"
end
tok = ""
break
when 0x28, 0x5B, 0x7B
# opening delimiter, start of new token
@tokens << tok if tok.size > 0
@tokens << byte.chr
tok = ""
break
when 0x29, 0x5D, 0x7D
# closing delimiter
@tokens << tok if tok.size > 0
@tokens << byte.chr
tok = ""
break
when 0x2F
# PDF name, start of new token
@tokens << tok if tok.size > 0
@tokens << byte.chr
@tokens << "" if byte == 0x2F && [nil, 0x20, 0x0A].include?(peek_byte)
tok = ""
break
else
tok << byte
end
end
@tokens << tok if tok.size > 0
end
# peek at the next character in the io stream, leaving the stream position
# untouched
#
def peek_byte
byte = @io.getbyte
@io.seek(-1, IO::SEEK_CUR) if byte
byte
end
# for a handful of tokens we want to tell the parser how to convert them
# into higher level tokens. This methods adds a to_token() method
# to tokens that should remain as strings.
#
def string_token(token)
def token.to_token
to_s
end
token
end
end
end
|