finishm 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (554) hide show
  1. checksums.yaml +7 -0
  2. data/.document +5 -0
  3. data/.gitmodules +3 -0
  4. data/.rspec +1 -0
  5. data/Gemfile +31 -0
  6. data/LICENSE.txt +20 -0
  7. data/README.md +59 -0
  8. data/Rakefile +51 -0
  9. data/VERSION +1 -0
  10. data/bin/assembly_visualiser +106 -0
  11. data/bin/check_primer_combinations.rb +73 -0
  12. data/bin/contig_joiner.rb +244 -0
  13. data/bin/contigs_against_assembly.rb +153 -0
  14. data/bin/finishm +143 -0
  15. data/bin/finishm_assembler +55 -0
  16. data/bin/finishm_gap_closer.rb +241 -0
  17. data/bin/kmer_abundance_file_tool.rb +49 -0
  18. data/bin/kmer_pattern_to_assembly.rb +377 -0
  19. data/bin/kmer_profile_finder.rb +92 -0
  20. data/bin/kmers_count_parse.d +52 -0
  21. data/bin/kmers_count_tabulate.d +123 -0
  22. data/bin/kmers_count_tabulate.rb +84 -0
  23. data/bin/pcr_result_parser.rb +108 -0
  24. data/bin/primer_finder.rb +119 -0
  25. data/bin/read_selection_by_kmer.d +174 -0
  26. data/bin/scaffold_by_pattern.rb +119 -0
  27. data/bin/scaffold_connection_possibilities_to_knowns.rb +193 -0
  28. data/bin/scaffold_end_coverages.rb +69 -0
  29. data/bin/trail_validator.rb +84 -0
  30. data/ext/mkrf_conf.rb +56 -0
  31. data/ext/src/Makefile +140 -0
  32. data/ext/src/src/allocArray.c +305 -0
  33. data/ext/src/src/allocArray.h +86 -0
  34. data/ext/src/src/autoOpen.c +107 -0
  35. data/ext/src/src/autoOpen.h +18 -0
  36. data/ext/src/src/binarySequences.c +813 -0
  37. data/ext/src/src/binarySequences.h +125 -0
  38. data/ext/src/src/concatenatedGraph.c +233 -0
  39. data/ext/src/src/concatenatedGraph.h +30 -0
  40. data/ext/src/src/concatenatedPreGraph.c +262 -0
  41. data/ext/src/src/concatenatedPreGraph.h +29 -0
  42. data/ext/src/src/correctedGraph.c +2643 -0
  43. data/ext/src/src/correctedGraph.h +32 -0
  44. data/ext/src/src/dfib.c +509 -0
  45. data/ext/src/src/dfib.h +69 -0
  46. data/ext/src/src/dfibHeap.c +89 -0
  47. data/ext/src/src/dfibHeap.h +39 -0
  48. data/ext/src/src/dfibpriv.h +105 -0
  49. data/ext/src/src/fib.c +628 -0
  50. data/ext/src/src/fib.h +78 -0
  51. data/ext/src/src/fibHeap.c +79 -0
  52. data/ext/src/src/fibHeap.h +41 -0
  53. data/ext/src/src/fibpriv.h +110 -0
  54. data/ext/src/src/globals.h +154 -0
  55. data/ext/src/src/graph.c +3932 -0
  56. data/ext/src/src/graph.h +233 -0
  57. data/ext/src/src/graphReConstruction.c +1472 -0
  58. data/ext/src/src/graphReConstruction.h +30 -0
  59. data/ext/src/src/graphStats.c +2167 -0
  60. data/ext/src/src/graphStats.h +72 -0
  61. data/ext/src/src/graphStructures.h +52 -0
  62. data/ext/src/src/kmer.c +652 -0
  63. data/ext/src/src/kmer.h +73 -0
  64. data/ext/src/src/kmerOccurenceTable.c +236 -0
  65. data/ext/src/src/kmerOccurenceTable.h +44 -0
  66. data/ext/src/src/kseq.h +223 -0
  67. data/ext/src/src/locallyCorrectedGraph.c +557 -0
  68. data/ext/src/src/locallyCorrectedGraph.h +40 -0
  69. data/ext/src/src/passageMarker.c +677 -0
  70. data/ext/src/src/passageMarker.h +137 -0
  71. data/ext/src/src/preGraph.c +1717 -0
  72. data/ext/src/src/preGraph.h +106 -0
  73. data/ext/src/src/preGraphConstruction.c +990 -0
  74. data/ext/src/src/preGraphConstruction.h +26 -0
  75. data/ext/src/src/probe_node_finder.c +84 -0
  76. data/ext/src/src/probe_node_finder.h +6 -0
  77. data/ext/src/src/readCoherentGraph.c +557 -0
  78. data/ext/src/src/readCoherentGraph.h +30 -0
  79. data/ext/src/src/readSet.c +1734 -0
  80. data/ext/src/src/readSet.h +67 -0
  81. data/ext/src/src/readToNode.c +218 -0
  82. data/ext/src/src/readToNode.h +35 -0
  83. data/ext/src/src/recycleBin.c +199 -0
  84. data/ext/src/src/recycleBin.h +58 -0
  85. data/ext/src/src/roadMap.c +342 -0
  86. data/ext/src/src/roadMap.h +65 -0
  87. data/ext/src/src/run.c +318 -0
  88. data/ext/src/src/run.h +52 -0
  89. data/ext/src/src/run2.c +744 -0
  90. data/ext/src/src/runReadToNode.c +29 -0
  91. data/ext/src/src/scaffold.c +1876 -0
  92. data/ext/src/src/scaffold.h +64 -0
  93. data/ext/src/src/shortReadPairs.c +1243 -0
  94. data/ext/src/src/shortReadPairs.h +32 -0
  95. data/ext/src/src/splay.c +259 -0
  96. data/ext/src/src/splay.h +43 -0
  97. data/ext/src/src/splayTable.c +1315 -0
  98. data/ext/src/src/splayTable.h +31 -0
  99. data/ext/src/src/tightString.c +362 -0
  100. data/ext/src/src/tightString.h +82 -0
  101. data/ext/src/src/utility.c +199 -0
  102. data/ext/src/src/utility.h +98 -0
  103. data/ext/src/third-party/zlib-1.2.3/ChangeLog +855 -0
  104. data/ext/src/third-party/zlib-1.2.3/FAQ +339 -0
  105. data/ext/src/third-party/zlib-1.2.3/INDEX +51 -0
  106. data/ext/src/third-party/zlib-1.2.3/Makefile +154 -0
  107. data/ext/src/third-party/zlib-1.2.3/Makefile.in +154 -0
  108. data/ext/src/third-party/zlib-1.2.3/README +125 -0
  109. data/ext/src/third-party/zlib-1.2.3/adler32.c +149 -0
  110. data/ext/src/third-party/zlib-1.2.3/adler32.o +0 -0
  111. data/ext/src/third-party/zlib-1.2.3/algorithm.txt +209 -0
  112. data/ext/src/third-party/zlib-1.2.3/amiga/Makefile.pup +66 -0
  113. data/ext/src/third-party/zlib-1.2.3/amiga/Makefile.sas +65 -0
  114. data/ext/src/third-party/zlib-1.2.3/as400/bndsrc +132 -0
  115. data/ext/src/third-party/zlib-1.2.3/as400/compile.clp +123 -0
  116. data/ext/src/third-party/zlib-1.2.3/as400/readme.txt +111 -0
  117. data/ext/src/third-party/zlib-1.2.3/as400/zlib.inc +331 -0
  118. data/ext/src/third-party/zlib-1.2.3/compress.c +79 -0
  119. data/ext/src/third-party/zlib-1.2.3/compress.o +0 -0
  120. data/ext/src/third-party/zlib-1.2.3/configure +459 -0
  121. data/ext/src/third-party/zlib-1.2.3/contrib/README.contrib +71 -0
  122. data/ext/src/third-party/zlib-1.2.3/contrib/ada/buffer_demo.adb +106 -0
  123. data/ext/src/third-party/zlib-1.2.3/contrib/ada/mtest.adb +156 -0
  124. data/ext/src/third-party/zlib-1.2.3/contrib/ada/read.adb +156 -0
  125. data/ext/src/third-party/zlib-1.2.3/contrib/ada/readme.txt +65 -0
  126. data/ext/src/third-party/zlib-1.2.3/contrib/ada/test.adb +463 -0
  127. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib-streams.adb +225 -0
  128. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib-streams.ads +114 -0
  129. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib-thin.adb +141 -0
  130. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib-thin.ads +450 -0
  131. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib.adb +701 -0
  132. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib.ads +328 -0
  133. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib.gpr +20 -0
  134. data/ext/src/third-party/zlib-1.2.3/contrib/asm586/README.586 +43 -0
  135. data/ext/src/third-party/zlib-1.2.3/contrib/asm586/match.S +364 -0
  136. data/ext/src/third-party/zlib-1.2.3/contrib/asm686/README.686 +34 -0
  137. data/ext/src/third-party/zlib-1.2.3/contrib/asm686/match.S +329 -0
  138. data/ext/src/third-party/zlib-1.2.3/contrib/blast/Makefile +8 -0
  139. data/ext/src/third-party/zlib-1.2.3/contrib/blast/README +4 -0
  140. data/ext/src/third-party/zlib-1.2.3/contrib/blast/blast.c +444 -0
  141. data/ext/src/third-party/zlib-1.2.3/contrib/blast/blast.h +71 -0
  142. data/ext/src/third-party/zlib-1.2.3/contrib/blast/test.pk +0 -0
  143. data/ext/src/third-party/zlib-1.2.3/contrib/blast/test.txt +1 -0
  144. data/ext/src/third-party/zlib-1.2.3/contrib/delphi/ZLib.pas +557 -0
  145. data/ext/src/third-party/zlib-1.2.3/contrib/delphi/ZLibConst.pas +11 -0
  146. data/ext/src/third-party/zlib-1.2.3/contrib/delphi/readme.txt +76 -0
  147. data/ext/src/third-party/zlib-1.2.3/contrib/delphi/zlibd32.mak +93 -0
  148. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib.build +33 -0
  149. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib.chm +0 -0
  150. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib.sln +21 -0
  151. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/AssemblyInfo.cs +58 -0
  152. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/ChecksumImpl.cs +202 -0
  153. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/CircularBuffer.cs +83 -0
  154. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/CodecBase.cs +198 -0
  155. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/Deflater.cs +106 -0
  156. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/DotZLib.cs +288 -0
  157. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/DotZLib.csproj +141 -0
  158. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/GZipStream.cs +301 -0
  159. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/Inflater.cs +105 -0
  160. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/UnitTests.cs +274 -0
  161. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/LICENSE_1_0.txt +23 -0
  162. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/readme.txt +58 -0
  163. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/README +1 -0
  164. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/infback9.c +608 -0
  165. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/infback9.h +37 -0
  166. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/inffix9.h +107 -0
  167. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/inflate9.h +47 -0
  168. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/inftree9.c +323 -0
  169. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/inftree9.h +55 -0
  170. data/ext/src/third-party/zlib-1.2.3/contrib/inflate86/inffas86.c +1157 -0
  171. data/ext/src/third-party/zlib-1.2.3/contrib/inflate86/inffast.S +1368 -0
  172. data/ext/src/third-party/zlib-1.2.3/contrib/iostream/test.cpp +24 -0
  173. data/ext/src/third-party/zlib-1.2.3/contrib/iostream/zfstream.cpp +329 -0
  174. data/ext/src/third-party/zlib-1.2.3/contrib/iostream/zfstream.h +128 -0
  175. data/ext/src/third-party/zlib-1.2.3/contrib/iostream2/zstream.h +307 -0
  176. data/ext/src/third-party/zlib-1.2.3/contrib/iostream2/zstream_test.cpp +25 -0
  177. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/README +35 -0
  178. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/TODO +17 -0
  179. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/test.cc +50 -0
  180. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/zfstream.cc +479 -0
  181. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/zfstream.h +466 -0
  182. data/ext/src/third-party/zlib-1.2.3/contrib/masm686/match.asm +413 -0
  183. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/bld_ml64.bat +2 -0
  184. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/gvmat64.asm +513 -0
  185. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/gvmat64.obj +0 -0
  186. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/inffas8664.c +186 -0
  187. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/inffasx64.asm +392 -0
  188. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/inffasx64.obj +0 -0
  189. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/readme.txt +28 -0
  190. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/bld_ml32.bat +2 -0
  191. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/gvmat32.asm +972 -0
  192. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/gvmat32.obj +0 -0
  193. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/gvmat32c.c +62 -0
  194. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/inffas32.asm +1083 -0
  195. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/inffas32.obj +0 -0
  196. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/mkasm.bat +3 -0
  197. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/readme.txt +21 -0
  198. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/ChangeLogUnzip +67 -0
  199. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/Makefile +25 -0
  200. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/crypt.h +132 -0
  201. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/ioapi.c +177 -0
  202. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/ioapi.h +75 -0
  203. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/iowin32.c +270 -0
  204. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/iowin32.h +21 -0
  205. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/miniunz.c +585 -0
  206. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/minizip.c +420 -0
  207. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/mztools.c +281 -0
  208. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/mztools.h +31 -0
  209. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/unzip.c +1598 -0
  210. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/unzip.h +354 -0
  211. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/zip.c +1219 -0
  212. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/zip.h +235 -0
  213. data/ext/src/third-party/zlib-1.2.3/contrib/pascal/example.pas +599 -0
  214. data/ext/src/third-party/zlib-1.2.3/contrib/pascal/readme.txt +76 -0
  215. data/ext/src/third-party/zlib-1.2.3/contrib/pascal/zlibd32.mak +93 -0
  216. data/ext/src/third-party/zlib-1.2.3/contrib/pascal/zlibpas.pas +236 -0
  217. data/ext/src/third-party/zlib-1.2.3/contrib/puff/Makefile +8 -0
  218. data/ext/src/third-party/zlib-1.2.3/contrib/puff/README +63 -0
  219. data/ext/src/third-party/zlib-1.2.3/contrib/puff/puff.c +837 -0
  220. data/ext/src/third-party/zlib-1.2.3/contrib/puff/puff.h +31 -0
  221. data/ext/src/third-party/zlib-1.2.3/contrib/puff/zeros.raw +0 -0
  222. data/ext/src/third-party/zlib-1.2.3/contrib/testzlib/testzlib.c +275 -0
  223. data/ext/src/third-party/zlib-1.2.3/contrib/testzlib/testzlib.txt +10 -0
  224. data/ext/src/third-party/zlib-1.2.3/contrib/untgz/Makefile +14 -0
  225. data/ext/src/third-party/zlib-1.2.3/contrib/untgz/Makefile.msc +17 -0
  226. data/ext/src/third-party/zlib-1.2.3/contrib/untgz/untgz.c +674 -0
  227. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/readme.txt +73 -0
  228. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/miniunz.vcproj +126 -0
  229. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/minizip.vcproj +126 -0
  230. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/testzlib.vcproj +126 -0
  231. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlib.rc +32 -0
  232. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlibstat.vcproj +246 -0
  233. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlibvc.def +92 -0
  234. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlibvc.sln +78 -0
  235. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlibvc.vcproj +445 -0
  236. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/miniunz.vcproj +566 -0
  237. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/minizip.vcproj +563 -0
  238. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/testzlib.vcproj +948 -0
  239. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/testzlibdll.vcproj +567 -0
  240. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlib.rc +32 -0
  241. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlibstat.vcproj +870 -0
  242. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlibvc.def +92 -0
  243. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlibvc.sln +144 -0
  244. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlibvc.vcproj +1219 -0
  245. data/ext/src/third-party/zlib-1.2.3/crc32.c +423 -0
  246. data/ext/src/third-party/zlib-1.2.3/crc32.h +441 -0
  247. data/ext/src/third-party/zlib-1.2.3/crc32.o +0 -0
  248. data/ext/src/third-party/zlib-1.2.3/deflate.c +1736 -0
  249. data/ext/src/third-party/zlib-1.2.3/deflate.h +331 -0
  250. data/ext/src/third-party/zlib-1.2.3/deflate.o +0 -0
  251. data/ext/src/third-party/zlib-1.2.3/example +0 -0
  252. data/ext/src/third-party/zlib-1.2.3/example.c +565 -0
  253. data/ext/src/third-party/zlib-1.2.3/examples/README.examples +42 -0
  254. data/ext/src/third-party/zlib-1.2.3/examples/fitblk.c +233 -0
  255. data/ext/src/third-party/zlib-1.2.3/examples/gun.c +693 -0
  256. data/ext/src/third-party/zlib-1.2.3/examples/gzappend.c +500 -0
  257. data/ext/src/third-party/zlib-1.2.3/examples/gzjoin.c +448 -0
  258. data/ext/src/third-party/zlib-1.2.3/examples/gzlog.c +413 -0
  259. data/ext/src/third-party/zlib-1.2.3/examples/gzlog.h +58 -0
  260. data/ext/src/third-party/zlib-1.2.3/examples/zlib_how.html +523 -0
  261. data/ext/src/third-party/zlib-1.2.3/examples/zpipe.c +191 -0
  262. data/ext/src/third-party/zlib-1.2.3/examples/zran.c +404 -0
  263. data/ext/src/third-party/zlib-1.2.3/gzio.c +1026 -0
  264. data/ext/src/third-party/zlib-1.2.3/gzio.o +0 -0
  265. data/ext/src/third-party/zlib-1.2.3/infback.c +623 -0
  266. data/ext/src/third-party/zlib-1.2.3/infback.o +0 -0
  267. data/ext/src/third-party/zlib-1.2.3/inffast.c +318 -0
  268. data/ext/src/third-party/zlib-1.2.3/inffast.h +11 -0
  269. data/ext/src/third-party/zlib-1.2.3/inffast.o +0 -0
  270. data/ext/src/third-party/zlib-1.2.3/inffixed.h +94 -0
  271. data/ext/src/third-party/zlib-1.2.3/inflate.c +1368 -0
  272. data/ext/src/third-party/zlib-1.2.3/inflate.h +115 -0
  273. data/ext/src/third-party/zlib-1.2.3/inflate.o +0 -0
  274. data/ext/src/third-party/zlib-1.2.3/inftrees.c +329 -0
  275. data/ext/src/third-party/zlib-1.2.3/inftrees.h +55 -0
  276. data/ext/src/third-party/zlib-1.2.3/inftrees.o +0 -0
  277. data/ext/src/third-party/zlib-1.2.3/libz.a +0 -0
  278. data/ext/src/third-party/zlib-1.2.3/make_vms.com +461 -0
  279. data/ext/src/third-party/zlib-1.2.3/minigzip +0 -0
  280. data/ext/src/third-party/zlib-1.2.3/minigzip.c +322 -0
  281. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.bor +109 -0
  282. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.dj2 +104 -0
  283. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.emx +69 -0
  284. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.msc +106 -0
  285. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.tc +94 -0
  286. data/ext/src/third-party/zlib-1.2.3/old/Makefile.riscos +151 -0
  287. data/ext/src/third-party/zlib-1.2.3/old/README +3 -0
  288. data/ext/src/third-party/zlib-1.2.3/old/descrip.mms +48 -0
  289. data/ext/src/third-party/zlib-1.2.3/old/os2/Makefile.os2 +136 -0
  290. data/ext/src/third-party/zlib-1.2.3/old/os2/zlib.def +51 -0
  291. data/ext/src/third-party/zlib-1.2.3/old/visual-basic.txt +160 -0
  292. data/ext/src/third-party/zlib-1.2.3/old/zlib.html +971 -0
  293. data/ext/src/third-party/zlib-1.2.3/projects/README.projects +41 -0
  294. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/README.txt +73 -0
  295. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/example.dsp +278 -0
  296. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/minigzip.dsp +278 -0
  297. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/zlib.dsp +609 -0
  298. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/zlib.dsw +59 -0
  299. data/ext/src/third-party/zlib-1.2.3/qnx/package.qpg +141 -0
  300. data/ext/src/third-party/zlib-1.2.3/trees.c +1219 -0
  301. data/ext/src/third-party/zlib-1.2.3/trees.h +128 -0
  302. data/ext/src/third-party/zlib-1.2.3/trees.o +0 -0
  303. data/ext/src/third-party/zlib-1.2.3/uncompr.c +61 -0
  304. data/ext/src/third-party/zlib-1.2.3/uncompr.o +0 -0
  305. data/ext/src/third-party/zlib-1.2.3/win32/DLL_FAQ.txt +397 -0
  306. data/ext/src/third-party/zlib-1.2.3/win32/Makefile.bor +107 -0
  307. data/ext/src/third-party/zlib-1.2.3/win32/Makefile.emx +69 -0
  308. data/ext/src/third-party/zlib-1.2.3/win32/Makefile.gcc +141 -0
  309. data/ext/src/third-party/zlib-1.2.3/win32/Makefile.msc +126 -0
  310. data/ext/src/third-party/zlib-1.2.3/win32/VisualC.txt +3 -0
  311. data/ext/src/third-party/zlib-1.2.3/win32/zlib.def +60 -0
  312. data/ext/src/third-party/zlib-1.2.3/win32/zlib1.rc +39 -0
  313. data/ext/src/third-party/zlib-1.2.3/zconf.h +332 -0
  314. data/ext/src/third-party/zlib-1.2.3/zconf.in.h +332 -0
  315. data/ext/src/third-party/zlib-1.2.3/zlib.3 +159 -0
  316. data/ext/src/third-party/zlib-1.2.3/zlib.h +1357 -0
  317. data/ext/src/third-party/zlib-1.2.3/zutil.c +318 -0
  318. data/ext/src/third-party/zlib-1.2.3/zutil.h +269 -0
  319. data/ext/src/third-party/zlib-1.2.3/zutil.o +0 -0
  320. data/lib/assembly/a_b_visualiser.rb +169 -0
  321. data/lib/assembly/acyclic_connection_finder.rb +81 -0
  322. data/lib/assembly/all_orfs.rb +615 -0
  323. data/lib/assembly/bad_format_writer.rb +46 -0
  324. data/lib/assembly/bam_probe_read_selector.rb +48 -0
  325. data/lib/assembly/bubbly_assembler.rb +842 -0
  326. data/lib/assembly/c_probe_node_finder.rb +38 -0
  327. data/lib/assembly/connection_interpreter.rb +350 -0
  328. data/lib/assembly/contig_printer.rb +400 -0
  329. data/lib/assembly/coverage_based_graph_filter.rb +68 -0
  330. data/lib/assembly/depth_first_search.rb +63 -0
  331. data/lib/assembly/dijkstra.rb +216 -0
  332. data/lib/assembly/fluffer.rb +253 -0
  333. data/lib/assembly/graph_explorer.rb +85 -0
  334. data/lib/assembly/graph_generator.rb +315 -0
  335. data/lib/assembly/height_finder.rb +355 -0
  336. data/lib/assembly/hybrid_velvet_graph.rb +70 -0
  337. data/lib/assembly/input_genome.rb +182 -0
  338. data/lib/assembly/kmer_coverage_based_path_filter.rb +65 -0
  339. data/lib/assembly/node_finder.rb +171 -0
  340. data/lib/assembly/oriented_node_trail.rb +507 -0
  341. data/lib/assembly/paired_end_assembler.rb +53 -0
  342. data/lib/assembly/paired_end_neighbour_finder.rb +176 -0
  343. data/lib/assembly/probed_graph.rb +105 -0
  344. data/lib/assembly/read_input.rb +79 -0
  345. data/lib/assembly/read_to_node.rb +37 -0
  346. data/lib/assembly/scaffold_breaker.rb +126 -0
  347. data/lib/assembly/sequence_hasher.rb +71 -0
  348. data/lib/assembly/single_coherent_paths_between_nodes.rb +533 -0
  349. data/lib/assembly/single_coherent_wanderer.rb +261 -0
  350. data/lib/assembly/single_ended_assembler.rb +441 -0
  351. data/lib/assembly/velvet_c_binding.rb +54 -0
  352. data/lib/assembly/velvet_graph_sequence_extractor.rb +123 -0
  353. data/lib/external/VERSION +1 -0
  354. data/lib/finishm/assemble.rb +224 -0
  355. data/lib/finishm/explore.rb +217 -0
  356. data/lib/finishm/finisher.rb +303 -0
  357. data/lib/finishm/fluff.rb +122 -0
  358. data/lib/finishm/gapfiller.rb +325 -0
  359. data/lib/finishm/orfs_finder.rb +88 -0
  360. data/lib/finishm/path_counter.rb +90 -0
  361. data/lib/finishm/primers.rb +425 -0
  362. data/lib/finishm/primers_check.rb +176 -0
  363. data/lib/finishm/roundup.rb +344 -0
  364. data/lib/finishm/sequence.rb +142 -0
  365. data/lib/finishm/visualise.rb +430 -0
  366. data/lib/finishm/wander.rb +270 -0
  367. data/lib/kmer_abundance_pattern.rb +79 -0
  368. data/lib/kmer_multi_abundance_file.rb +48 -0
  369. data/lib/oligo_designer.rb +88 -0
  370. data/lib/priner.rb +66 -0
  371. data/spec/acyclic_connection_finder_spec.rb +551 -0
  372. data/spec/all_orfs_spec.rb +443 -0
  373. data/spec/assemble_spec.rb +186 -0
  374. data/spec/bubbly_assembler_spec.rb +707 -0
  375. data/spec/c_node_finder_spec.rb +58 -0
  376. data/spec/connection_interpreter_spec.rb +284 -0
  377. data/spec/contig_printer_spec.rb +291 -0
  378. data/spec/coverage_based_graph_filter_spec.rb +102 -0
  379. data/spec/data/6_3e4e5e6e.1vANME.bam +0 -0
  380. data/spec/data/6_3e4e5e6e.1vANME.bam.bai +0 -0
  381. data/spec/data/acyclic_connection_finder/1/probes.fa +5 -0
  382. data/spec/data/acyclic_connection_finder/1/random1.fa +2 -0
  383. data/spec/data/acyclic_connection_finder/1/random1.sammy.fa.gz +0 -0
  384. data/spec/data/acyclic_connection_finder/1/random2.fa +2 -0
  385. data/spec/data/acyclic_connection_finder/1/random2.sammy.fa.gz +0 -0
  386. data/spec/data/assembly/1_simple_bubble_uneven_coverage/random3000.fa +39 -0
  387. data/spec/data/assembly/1_simple_bubble_uneven_coverage/random3000.slightly_changed.fa +39 -0
  388. data/spec/data/assembly/1_simple_bubble_uneven_coverage/reads_combined.fa.gz +0 -0
  389. data/spec/data/assembly_visualiser/Contig_6_1_to_250.fa.kmers31 +220 -0
  390. data/spec/data/assembly_visualiser/Contig_7_1_to_250.fa.kmers31 +220 -0
  391. data/spec/data/assembly_visualiser/Graph +46 -0
  392. data/spec/data/assembly_visualiser/start_kmers1 +2 -0
  393. data/spec/data/bands.csv +1 -0
  394. data/spec/data/c_probe_node_finder/1/CnyUnifiedSeq +0 -0
  395. data/spec/data/c_probe_node_finder/1/CnyUnifiedSeq.names +544 -0
  396. data/spec/data/c_probe_node_finder/1/Graph2 +668 -0
  397. data/spec/data/c_probe_node_finder/1/LastGraph +668 -0
  398. data/spec/data/c_probe_node_finder/1/Log +756 -0
  399. data/spec/data/c_probe_node_finder/1/PreGraph +11 -0
  400. data/spec/data/c_probe_node_finder/1/Roadmaps +2009 -0
  401. data/spec/data/c_probe_node_finder/1/contigs.fa +29 -0
  402. data/spec/data/c_probe_node_finder/1/stats.txt +6 -0
  403. data/spec/data/contig_printer/1/HOWTO_RECREATE +17 -0
  404. data/spec/data/contig_printer/1/contigs.fa +4 -0
  405. data/spec/data/contig_printer/1/seq.fa +2408 -0
  406. data/spec/data/contig_printer/1/seq.fa.svg +153 -0
  407. data/spec/data/contig_printer/1/seq.fa.velvet/Graph2 +2953 -0
  408. data/spec/data/contig_printer/1/seq.fa.velvet/LastGraph +2953 -0
  409. data/spec/data/contig_printer/1/seq.fa.velvet/Log +21 -0
  410. data/spec/data/contig_printer/1/seq.fa.velvet/PreGraph +27 -0
  411. data/spec/data/contig_printer/1/seq.fa.velvet/Roadmaps +5182 -0
  412. data/spec/data/contig_printer/1/seq.fa.velvet/Sequences +3612 -0
  413. data/spec/data/contig_printer/1/seq.fa.velvet/contigs.fa +36 -0
  414. data/spec/data/contig_printer/1/seq.fa.velvet/stats.txt +14 -0
  415. data/spec/data/contig_printer/1/seq.faVseq2_1to550.fa.bam +0 -0
  416. data/spec/data/contig_printer/1/seq.faVseq2_1to550.fa.bam.bai +0 -0
  417. data/spec/data/contig_printer/1/seq.node12.fa +4 -0
  418. data/spec/data/contig_printer/1/seq1_1to550.fa +2 -0
  419. data/spec/data/contig_printer/1/seq2_1to550.fa +2 -0
  420. data/spec/data/contig_printer/1/seq2_1to550.fa.fai +1 -0
  421. data/spec/data/explore/1/2seqs.sammy.fa +12004 -0
  422. data/spec/data/explore/1/HOWTO_RECREATE.txt +6 -0
  423. data/spec/data/explore/1/a.fa +2 -0
  424. data/spec/data/explore/1/seq1_and_a.fa +3 -0
  425. data/spec/data/explore/1/seq2.fa +2 -0
  426. data/spec/data/fluff/1/2seqs.sammy.fa +12004 -0
  427. data/spec/data/fluff/1/HOWTO_RECREATE.txt +5 -0
  428. data/spec/data/fluff/1/seq1.fa +2 -0
  429. data/spec/data/fluff/1/seq2.fa +2 -0
  430. data/spec/data/gapfilling/1/reads.fa +171 -0
  431. data/spec/data/gapfilling/1/trail_with_Ns.fa +5 -0
  432. data/spec/data/gapfilling/1/velvetAssembly/Graph2 +130 -0
  433. data/spec/data/gapfilling/1/velvetAssembly/LastGraph +130 -0
  434. data/spec/data/gapfilling/1/velvetAssembly/Log +199 -0
  435. data/spec/data/gapfilling/1/velvetAssembly/PreGraph +7 -0
  436. data/spec/data/gapfilling/1/velvetAssembly/Roadmaps +239 -0
  437. data/spec/data/gapfilling/1/velvetAssembly/Sequences +281 -0
  438. data/spec/data/gapfilling/1/velvetAssembly/contigs.fa +12 -0
  439. data/spec/data/gapfilling/1/velvetAssembly/stats.txt +4 -0
  440. data/spec/data/gapfilling/2/HOWTO_recreate +17 -0
  441. data/spec/data/gapfilling/2/reference.fa +2 -0
  442. data/spec/data/gapfilling/2/reference_part1.fa +4 -0
  443. data/spec/data/gapfilling/2/reference_part2.fa +4 -0
  444. data/spec/data/gapfilling/2/sammy_reads.fa.gz +0 -0
  445. data/spec/data/gapfilling/2/with_gaps.fa +4 -0
  446. data/spec/data/gapfilling/3/HOWTO_recreate +4 -0
  447. data/spec/data/gapfilling/3/reads.fa.gz +0 -0
  448. data/spec/data/gapfilling/3/reference_part1.fa +4 -0
  449. data/spec/data/gapfilling/3/reference_part2.fa +4 -0
  450. data/spec/data/gapfilling/3/with_gaps.fa +4 -0
  451. data/spec/data/gapfilling/4/HOWTO_recreate +1 -0
  452. data/spec/data/gapfilling/4/reads.fa.gz +0 -0
  453. data/spec/data/gapfilling/5/HOWTO_RECREATE +7 -0
  454. data/spec/data/gapfilling/5/answer.fna +2 -0
  455. data/spec/data/gapfilling/5/gappy.fna +2 -0
  456. data/spec/data/gapfilling/5/reads.fa +17961 -0
  457. data/spec/data/gapfilling/5/velvet51_3.5/LastGraph +8337 -0
  458. data/spec/data/gapfilling/5/velvet51_3.5/Sequences +20921 -0
  459. data/spec/data/gapfilling/6/random1.fa +28 -0
  460. data/spec/data/gapfilling/6/random2.fa +28 -0
  461. data/spec/data/gapfilling/6/random_sequence_length_2000 +0 -0
  462. data/spec/data/gapfilling/6/reads.random1.fa.gz +0 -0
  463. data/spec/data/gapfilling/6/reads.random2.fa.gz +0 -0
  464. data/spec/data/gapfilling/6/to_gapfill.fa +22 -0
  465. data/spec/data/kmer_profile_to_assembly/multiple_abundance_file1.csv +2 -0
  466. data/spec/data/kmers_count1.csv +2 -0
  467. data/spec/data/kmers_count2.csv +3 -0
  468. data/spec/data/out +3 -0
  469. data/spec/data/positive_latching_pair.fa +2 -0
  470. data/spec/data/primers.csv +4 -0
  471. data/spec/data/read_selection_by_kmer/blacklist1.txt +1 -0
  472. data/spec/data/read_selection_by_kmer/input.fasta +6 -0
  473. data/spec/data/read_selection_by_kmer/whitelist1.txt +1 -0
  474. data/spec/data/read_selection_by_kmer/whitelist2.txt +2 -0
  475. data/spec/data/read_to_node/1_a_graph/HOWTO_RECREATE.txt +2 -0
  476. data/spec/data/read_to_node/1_a_graph/LastGraph +6695 -0
  477. data/spec/data/read_to_node/1_a_graph/ReadToNode.bin +0 -0
  478. data/spec/data/read_to_node/2_no_read256_or_259/HOWTO_RECREATE.txt +3 -0
  479. data/spec/data/read_to_node/2_no_read256_or_259/LastGraph +6693 -0
  480. data/spec/data/read_to_node/2_no_read256_or_259/ReadToNode.bin +0 -0
  481. data/spec/data/read_to_node/3_no_last_read/LastGraph +6694 -0
  482. data/spec/data/read_to_node/3_no_last_read/ReadToNode.bin +0 -0
  483. data/spec/data/t/details.txt +5 -0
  484. data/spec/data/t/details.txt.srt +5 -0
  485. data/spec/data/t/location.txt +3 -0
  486. data/spec/data/t/location.txt.srt +3 -0
  487. data/spec/data/tweak/1_gap_then_unscaffolded/answer.fa +2 -0
  488. data/spec/data/tweak/1_gap_then_unscaffolded/reads.fa.gz +0 -0
  489. data/spec/data/tweak/1_gap_then_unscaffolded/scaffolds.fa +6 -0
  490. data/spec/data/tweak/2_second_genome/answer2.fa +2 -0
  491. data/spec/data/tweak/2_second_genome/reads.fa.gz +0 -0
  492. data/spec/data/tweak/3_variant/answer.fa +2 -0
  493. data/spec/data/tweak/3_variant/lesser_answer.fa +2 -0
  494. data/spec/data/tweak/3_variant/reads.fa.gz +0 -0
  495. data/spec/data/tweak/3_variant/with_gaps.fa +2 -0
  496. data/spec/data/velvet_test_trails/Assem/Graph +17 -0
  497. data/spec/data/velvet_test_trails/Assem/Graph2 +40 -0
  498. data/spec/data/velvet_test_trails/Assem/LastGraph +40 -0
  499. data/spec/data/velvet_test_trails/Assem/Log +35 -0
  500. data/spec/data/velvet_test_trails/Assem/PreGraph +9 -0
  501. data/spec/data/velvet_test_trails/Assem/Roadmaps +89 -0
  502. data/spec/data/velvet_test_trails/Assem/Sequences +50 -0
  503. data/spec/data/velvet_test_trails/Assem/a.svg +53 -0
  504. data/spec/data/velvet_test_trails/Assem/contigs.fa +15 -0
  505. data/spec/data/velvet_test_trails/Assem/stats.txt +5 -0
  506. data/spec/data/velvet_test_trails/node_fwds.fa +8 -0
  507. data/spec/data/velvet_test_trails/node_seqs.fa +9 -0
  508. data/spec/data/velvet_test_trails/nodes_fwd_rev.fa +16 -0
  509. data/spec/data/velvet_test_trails/read1.fa +2 -0
  510. data/spec/data/velvet_test_trails/reads.fa +50 -0
  511. data/spec/data/velvet_test_trails_reverse/Assem/LastGraph +17 -0
  512. data/spec/data/velvet_test_trails_reverse/Assem/a.svg +53 -0
  513. data/spec/data/velvet_test_trails_reverse/reads_reversed.fa +10 -0
  514. data/spec/data/visualise/1/LastGraph +6695 -0
  515. data/spec/data/visualise/2_paired_end/HOWTO_RECREATE.txt +10 -0
  516. data/spec/data/visualise/2_paired_end/rand1.fa +2 -0
  517. data/spec/data/visualise/2_paired_end/rand2.fa +2 -0
  518. data/spec/data/visualise/2_paired_end/with_gaps.fa +8 -0
  519. data/spec/data/visualise/2_paired_end/with_gaps.read_pairs.fa.gz +0 -0
  520. data/spec/data/wander/1/random1.fa +2 -0
  521. data/spec/data/wander/1/random1.sammy.fa +804 -0
  522. data/spec/depth_first_search_spec.rb +190 -0
  523. data/spec/dijkstra_spec.rb +143 -0
  524. data/spec/explore_spec.rb +29 -0
  525. data/spec/fluffer_spec.rb +155 -0
  526. data/spec/gapfiller_spec.rb +107 -0
  527. data/spec/graph_explorer_spec.rb +475 -0
  528. data/spec/graph_generator_spec.rb +99 -0
  529. data/spec/height_finder_spec.rb +306 -0
  530. data/spec/kmer_abundance_pattern_spec.rb +56 -0
  531. data/spec/kmer_coverage_based_path_filter_spec.rb +73 -0
  532. data/spec/kmer_profile_finder_spec.rb +38 -0
  533. data/spec/kmers_count_tabulate_spec.rb +120 -0
  534. data/spec/oriented_node_trail_spec.rb +221 -0
  535. data/spec/paired_end_neighbours_spec.rb +126 -0
  536. data/spec/paths_between_nodes_spec.rb +349 -0
  537. data/spec/priner_spec.rb +7 -0
  538. data/spec/read_input_spec.rb +23 -0
  539. data/spec/read_selection_by_kmer_spec.rb +166 -0
  540. data/spec/read_to_node_spec.rb +35 -0
  541. data/spec/roundup_spec.rb +366 -0
  542. data/spec/scaffold_breaker_spec.rb +144 -0
  543. data/spec/sequence_spec.rb +43 -0
  544. data/spec/single_coherent_paths_between_nodes_spec.rb +492 -0
  545. data/spec/single_coherent_wanderer_spec.rb +120 -0
  546. data/spec/single_ended_assembler_spec.rb +398 -0
  547. data/spec/spec_helper.rb +310 -0
  548. data/spec/velvet_graph_sequence_extractor_spec.rb +80 -0
  549. data/spec/visualise_spec.rb +105 -0
  550. data/spec/wander_spec.rb +119 -0
  551. data/spec/watch_for_changes.sh +16 -0
  552. data/validation/fasta_compare.rb +72 -0
  553. data/validation/gapfill_simulate_perfect.rb +108 -0
  554. metadata +899 -0
data/ext/src/third-party/zlib-1.2.3/examples/gzlog.h ADDED
@@ -0,0 +1,58 @@
1
+ /* gzlog.h
2
+ Copyright (C) 2004 Mark Adler, all rights reserved
3
+ version 1.0, 26 Nov 2004
4
+
5
+ This software is provided 'as-is', without any express or implied
6
+ warranty. In no event will the author be held liable for any damages
7
+ arising from the use of this software.
8
+
9
+ Permission is granted to anyone to use this software for any purpose,
10
+ including commercial applications, and to alter it and redistribute it
11
+ freely, subject to the following restrictions:
12
+
13
+ 1. The origin of this software must not be misrepresented; you must not
14
+ claim that you wrote the original software. If you use this software
15
+ in a product, an acknowledgment in the product documentation would be
16
+ appreciated but is not required.
17
+ 2. Altered source versions must be plainly marked as such, and must not be
18
+ misrepresented as being the original software.
19
+ 3. This notice may not be removed or altered from any source distribution.
20
+
21
+ Mark Adler madler@alumni.caltech.edu
22
+ */
23
+
24
+ /*
25
+ The gzlog object allows writing short messages to a gzipped log file,
26
+ opening the log file locked for small bursts, and then closing it. The log
27
+ object works by appending stored data to the gzip file until 1 MB has been
28
+ accumulated. At that time, the stored data is compressed, and replaces the
29
+ uncompressed data in the file. The log file is truncated to its new size at
30
+ that time. After closing, the log file is always valid gzip file that can
31
+ decompressed to recover what was written.
32
+
33
+ A gzip header "extra" field contains two file offsets for appending. The
34
+ first points to just after the last compressed data. The second points to
35
+ the last stored block in the deflate stream, which is empty. All of the
36
+ data between those pointers is uncompressed.
37
+ */
38
+
39
+ /* Open a gzlog object, creating the log file if it does not exist. Return
40
+ NULL on error. Note that gzlog_open() could take a long time to return if
41
+ there is difficulty in locking the file. */
42
+ void *gzlog_open(char *path);
43
+
44
+ /* Write to a gzlog object. Return non-zero on error. This function will
45
+ simply write data to the file uncompressed. Compression of the data
46
+ will not occur until gzlog_close() is called. It is expected that
47
+ gzlog_write() is used for a short message, and then gzlog_close() is
48
+ called. If a large amount of data is to be written, then the application
49
+ should write no more than 1 MB at a time with gzlog_write() before
50
+ calling gzlog_close() and then gzlog_open() again. */
51
+ int gzlog_write(void *log, char *data, size_t len);
52
+
53
+ /* Close a gzlog object. Return non-zero on error. The log file is locked
54
+ until this function is called. This function will compress stored data
55
+ at the end of the gzip file if at least 1 MB has been accumulated. Note
56
+ that the file will not be a valid gzip file until this function completes.
57
+ */
58
+ int gzlog_close(void *log);
data/ext/src/third-party/zlib-1.2.3/examples/zlib_how.html ADDED
@@ -0,0 +1,523 @@
1
+ <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
2
+ "http://www.w3.org/TR/REC-html40/loose.dtd">
3
+ <html>
4
+ <head>
5
+ <meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
6
+ <title>zlib Usage Example</title>
7
+ <!-- Copyright (c) 2004 Mark Adler. -->
8
+ </head>
9
+ <body bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#00A000">
10
+ <h2 align="center"> zlib Usage Example </h2>
11
+ We often get questions about how the <tt>deflate()</tt> and <tt>inflate()</tt> functions should be used.
12
+ Users wonder when they should provide more input, when they should use more output,
13
+ what to do with a <tt>Z_BUF_ERROR</tt>, how to make sure the process terminates properly, and
14
+ so on. So for those who have read <tt>zlib.h</tt> (a few times), and
15
+ would like further edification, below is an annotated example in C of simple routines to compress and decompress
16
+ from an input file to an output file using <tt>deflate()</tt> and <tt>inflate()</tt> respectively. The
17
+ annotations are interspersed between lines of the code. So please read between the lines.
18
+ We hope this helps explain some of the intricacies of <em>zlib</em>.
19
+ <p>
20
+ Without further adieu, here is the program <a href="zpipe.c"><tt>zpipe.c</tt></a>:
21
+ <pre><b>
22
+ /* zpipe.c: example of proper use of zlib's inflate() and deflate()
23
+ Not copyrighted -- provided to the public domain
24
+ Version 1.2 9 November 2004 Mark Adler */
25
+
26
+ /* Version history:
27
+ 1.0 30 Oct 2004 First version
28
+ 1.1 8 Nov 2004 Add void casting for unused return values
29
+ Use switch statement for inflate() return values
30
+ 1.2 9 Nov 2004 Add assertions to document zlib guarantees
31
+ */
32
+ </b></pre><!-- -->
33
+ We now include the header files for the required definitions. From
34
+ <tt>stdio.h</tt> we use <tt>fopen()</tt>, <tt>fread()</tt>, <tt>fwrite()</tt>,
35
+ <tt>feof()</tt>, <tt>ferror()</tt>, and <tt>fclose()</tt> for file i/o, and
36
+ <tt>fputs()</tt> for error messages. From <tt>string.h</tt> we use
37
+ <tt>strcmp()</tt> for command line argument processing.
38
+ From <tt>assert.h</tt> we use the <tt>assert()</tt> macro.
39
+ From <tt>zlib.h</tt>
40
+ we use the basic compression functions <tt>deflateInit()</tt>,
41
+ <tt>deflate()</tt>, and <tt>deflateEnd()</tt>, and the basic decompression
42
+ functions <tt>inflateInit()</tt>, <tt>inflate()</tt>, and
43
+ <tt>inflateEnd()</tt>.
44
+ <pre><b>
45
+ #include &lt;stdio.h&gt;
46
+ #include &lt;string.h&gt;
47
+ #include &lt;assert.h&gt;
48
+ #include "zlib.h"
49
+ </b></pre><!-- -->
50
+ <tt>CHUNK</tt> is simply the buffer size for feeding data to and pulling data
51
+ from the <em>zlib</em> routines. Larger buffer sizes would be more efficient,
52
+ especially for <tt>inflate()</tt>. If the memory is available, buffers sizes
53
+ on the order of 128K or 256K bytes should be used.
54
+ <pre><b>
55
+ #define CHUNK 16384
56
+ </b></pre><!-- -->
57
+ The <tt>def()</tt> routine compresses data from an input file to an output file. The output data
58
+ will be in the <em>zlib</em> format, which is different from the <em>gzip</em> or <em>zip</em>
59
+ formats. The <em>zlib</em> format has a very small header of only two bytes to identify it as
60
+ a <em>zlib</em> stream and to provide decoding information, and a four-byte trailer with a fast
61
+ check value to verify the integrity of the uncompressed data after decoding.
62
+ <pre><b>
63
+ /* Compress from file source to file dest until EOF on source.
64
+ def() returns Z_OK on success, Z_MEM_ERROR if memory could not be
65
+ allocated for processing, Z_STREAM_ERROR if an invalid compression
66
+ level is supplied, Z_VERSION_ERROR if the version of zlib.h and the
67
+ version of the library linked do not match, or Z_ERRNO if there is
68
+ an error reading or writing the files. */
69
+ int def(FILE *source, FILE *dest, int level)
70
+ {
71
+ </b></pre>
72
+ Here are the local variables for <tt>def()</tt>. <tt>ret</tt> will be used for <em>zlib</em>
73
+ return codes. <tt>flush</tt> will keep track of the current flushing state for <tt>deflate()</tt>,
74
+ which is either no flushing, or flush to completion after the end of the input file is reached.
75
+ <tt>have</tt> is the amount of data returned from <tt>deflate()</tt>. The <tt>strm</tt> structure
76
+ is used to pass information to and from the <em>zlib</em> routines, and to maintain the
77
+ <tt>deflate()</tt> state. <tt>in</tt> and <tt>out</tt> are the input and output buffers for
78
+ <tt>deflate()</tt>.
79
+ <pre><b>
80
+ int ret, flush;
81
+ unsigned have;
82
+ z_stream strm;
83
+ char in[CHUNK];
84
+ char out[CHUNK];
85
+ </b></pre><!-- -->
86
+ The first thing we do is to initialize the <em>zlib</em> state for compression using
87
+ <tt>deflateInit()</tt>. This must be done before the first use of <tt>deflate()</tt>.
88
+ The <tt>zalloc</tt>, <tt>zfree</tt>, and <tt>opaque</tt> fields in the <tt>strm</tt>
89
+ structure must be initialized before calling <tt>deflateInit()</tt>. Here they are
90
+ set to the <em>zlib</em> constant <tt>Z_NULL</tt> to request that <em>zlib</em> use
91
+ the default memory allocation routines. An application may also choose to provide
92
+ custom memory allocation routines here. <tt>deflateInit()</tt> will allocate on the
93
+ order of 256K bytes for the internal state.
94
+ (See <a href="zlib_tech.html"><em>zlib Technical Details</em></a>.)
95
+ <p>
96
+ <tt>deflateInit()</tt> is called with a pointer to the structure to be initialized and
97
+ the compression level, which is an integer in the range of -1 to 9. Lower compression
98
+ levels result in faster execution, but less compression. Higher levels result in
99
+ greater compression, but slower execution. The <em>zlib</em> constant Z_DEFAULT_COMPRESSION,
100
+ equal to -1,
101
+ provides a good compromise between compression and speed and is equivalent to level 6.
102
+ Level 0 actually does no compression at all, and in fact expands the data slightly to produce
103
+ the <em>zlib</em> format (it is not a byte-for-byte copy of the input).
104
+ More advanced applications of <em>zlib</em>
105
+ may use <tt>deflateInit2()</tt> here instead. Such an application may want to reduce how
106
+ much memory will be used, at some price in compression. Or it may need to request a
107
+ <em>gzip</em> header and trailer instead of a <em>zlib</em> header and trailer, or raw
108
+ encoding with no header or trailer at all.
109
+ <p>
110
+ We must check the return value of <tt>deflateInit()</tt> against the <em>zlib</em> constant
111
+ <tt>Z_OK</tt> to make sure that it was able to
112
+ allocate memory for the internal state, and that the provided arguments were valid.
113
+ <tt>deflateInit()</tt> will also check that the version of <em>zlib</em> that the <tt>zlib.h</tt>
114
+ file came from matches the version of <em>zlib</em> actually linked with the program. This
115
+ is especially important for environments in which <em>zlib</em> is a shared library.
116
+ <p>
117
+ Note that an application can initialize multiple, independent <em>zlib</em> streams, which can
118
+ operate in parallel. The state information maintained in the structure allows the <em>zlib</em>
119
+ routines to be reentrant.
120
+ <pre><b>
121
+ /* allocate deflate state */
122
+ strm.zalloc = Z_NULL;
123
+ strm.zfree = Z_NULL;
124
+ strm.opaque = Z_NULL;
125
+ ret = deflateInit(&amp;strm, level);
126
+ if (ret != Z_OK)
127
+ return ret;
128
+ </b></pre><!-- -->
129
+ With the pleasantries out of the way, now we can get down to business. The outer <tt>do</tt>-loop
130
+ reads all of the input file and exits at the bottom of the loop once end-of-file is reached.
131
+ This loop contains the only call of <tt>deflate()</tt>. So we must make sure that all of the
132
+ input data has been processed and that all of the output data has been generated and consumed
133
+ before we fall out of the loop at the bottom.
134
+ <pre><b>
135
+ /* compress until end of file */
136
+ do {
137
+ </b></pre>
138
+ We start off by reading data from the input file. The number of bytes read is put directly
139
+ into <tt>avail_in</tt>, and a pointer to those bytes is put into <tt>next_in</tt>. We also
140
+ check to see if end-of-file on the input has been reached. If we are at the end of file, then <tt>flush</tt> is set to the
141
+ <em>zlib</em> constant <tt>Z_FINISH</tt>, which is later passed to <tt>deflate()</tt> to
142
+ indicate that this is the last chunk of input data to compress. We need to use <tt>feof()</tt>
143
+ to check for end-of-file as opposed to seeing if fewer than <tt>CHUNK</tt> bytes have been read. The
144
+ reason is that if the input file length is an exact multiple of <tt>CHUNK</tt>, we will miss
145
+ the fact that we got to the end-of-file, and not know to tell <tt>deflate()</tt> to finish
146
+ up the compressed stream. If we are not yet at the end of the input, then the <em>zlib</em>
147
+ constant <tt>Z_NO_FLUSH</tt> will be passed to <tt>deflate</tt> to indicate that we are still
148
+ in the middle of the uncompressed data.
149
+ <p>
150
+ If there is an error in reading from the input file, the process is aborted with
151
+ <tt>deflateEnd()</tt> being called to free the allocated <em>zlib</em> state before returning
152
+ the error. We wouldn't want a memory leak, now would we? <tt>deflateEnd()</tt> can be called
153
+ at any time after the state has been initialized. Once that's done, <tt>deflateInit()</tt> (or
154
+ <tt>deflateInit2()</tt>) would have to be called to start a new compression process. There is
155
+ no point here in checking the <tt>deflateEnd()</tt> return code. The deallocation can't fail.
156
+ <pre><b>
157
+ strm.avail_in = fread(in, 1, CHUNK, source);
158
+ if (ferror(source)) {
159
+ (void)deflateEnd(&amp;strm);
160
+ return Z_ERRNO;
161
+ }
162
+ flush = feof(source) ? Z_FINISH : Z_NO_FLUSH;
163
+ strm.next_in = in;
164
+ </b></pre><!-- -->
165
+ The inner <tt>do</tt>-loop passes our chunk of input data to <tt>deflate()</tt>, and then
166
+ keeps calling <tt>deflate()</tt> until it is done producing output. Once there is no more
167
+ new output, <tt>deflate()</tt> is guaranteed to have consumed all of the input, i.e.,
168
+ <tt>avail_in</tt> will be zero.
169
+ <pre><b>
170
+ /* run deflate() on input until output buffer not full, finish
171
+ compression if all of source has been read in */
172
+ do {
173
+ </b></pre>
174
+ Output space is provided to <tt>deflate()</tt> by setting <tt>avail_out</tt> to the number
175
+ of available output bytes and <tt>next_out</tt> to a pointer to that space.
176
+ <pre><b>
177
+ strm.avail_out = CHUNK;
178
+ strm.next_out = out;
179
+ </b></pre>
180
+ Now we call the compression engine itself, <tt>deflate()</tt>. It takes as many of the
181
+ <tt>avail_in</tt> bytes at <tt>next_in</tt> as it can process, and writes as many as
182
+ <tt>avail_out</tt> bytes to <tt>next_out</tt>. Those counters and pointers are then
183
+ updated past the input data consumed and the output data written. It is the amount of
184
+ output space available that may limit how much input is consumed.
185
+ Hence the inner loop to make sure that
186
+ all of the input is consumed by providing more output space each time. Since <tt>avail_in</tt>
187
+ and <tt>next_in</tt> are updated by <tt>deflate()</tt>, we don't have to mess with those
188
+ between <tt>deflate()</tt> calls until it's all used up.
189
+ <p>
190
+ The parameters to <tt>deflate()</tt> are a pointer to the <tt>strm</tt> structure containing
191
+ the input and output information and the internal compression engine state, and a parameter
192
+ indicating whether and how to flush data to the output. Normally <tt>deflate</tt> will consume
193
+ several K bytes of input data before producing any output (except for the header), in order
194
+ to accumulate statistics on the data for optimum compression. It will then put out a burst of
195
+ compressed data, and proceed to consume more input before the next burst. Eventually,
196
+ <tt>deflate()</tt>
197
+ must be told to terminate the stream, complete the compression with provided input data, and
198
+ write out the trailer check value. <tt>deflate()</tt> will continue to compress normally as long
199
+ as the flush parameter is <tt>Z_NO_FLUSH</tt>. Once the <tt>Z_FINISH</tt> parameter is provided,
200
+ <tt>deflate()</tt> will begin to complete the compressed output stream. However depending on how
201
+ much output space is provided, <tt>deflate()</tt> may have to be called several times until it
202
+ has provided the complete compressed stream, even after it has consumed all of the input. The flush
203
+ parameter must continue to be <tt>Z_FINISH</tt> for those subsequent calls.
204
+ <p>
205
+ There are other values of the flush parameter that are used in more advanced applications. You can
206
+ force <tt>deflate()</tt> to produce a burst of output that encodes all of the input data provided
207
+ so far, even if it wouldn't have otherwise, for example to control data latency on a link with
208
+ compressed data. You can also ask that <tt>deflate()</tt> do that as well as erase any history up to
209
+ that point so that what follows can be decompressed independently, for example for random access
210
+ applications. Both requests will degrade compression by an amount depending on how often such
211
+ requests are made.
212
+ <p>
213
+ <tt>deflate()</tt> has a return value that can indicate errors, yet we do not check it here. Why
214
+ not? Well, it turns out that <tt>deflate()</tt> can do no wrong here. Let's go through
215
+ <tt>deflate()</tt>'s return values and dispense with them one by one. The possible values are
216
+ <tt>Z_OK</tt>, <tt>Z_STREAM_END</tt>, <tt>Z_STREAM_ERROR</tt>, or <tt>Z_BUF_ERROR</tt>. <tt>Z_OK</tt>
217
+ is, well, ok. <tt>Z_STREAM_END</tt> is also ok and will be returned for the last call of
218
+ <tt>deflate()</tt>. This is already guaranteed by calling <tt>deflate()</tt> with <tt>Z_FINISH</tt>
219
+ until it has no more output. <tt>Z_STREAM_ERROR</tt> is only possible if the stream is not
220
+ initialized properly, but we did initialize it properly. There is no harm in checking for
221
+ <tt>Z_STREAM_ERROR</tt> here, for example to check for the possibility that some
222
+ other part of the application inadvertently clobbered the memory containing the <em>zlib</em> state.
223
+ <tt>Z_BUF_ERROR</tt> will be explained further below, but
224
+ suffice it to say that this is simply an indication that <tt>deflate()</tt> could not consume
225
+ more input or produce more output. <tt>deflate()</tt> can be called again with more output space
226
+ or more available input, which it will be in this code.
227
+ <pre><b>
228
+ ret = deflate(&amp;strm, flush); /* no bad return value */
229
+ assert(ret != Z_STREAM_ERROR); /* state not clobbered */
230
+ </b></pre>
231
+ Now we compute how much output <tt>deflate()</tt> provided on the last call, which is the
232
+ difference between how much space was provided before the call, and how much output space
233
+ is still available after the call. Then that data, if any, is written to the output file.
234
+ We can then reuse the output buffer for the next call of <tt>deflate()</tt>. Again if there
235
+ is a file i/o error, we call <tt>deflateEnd()</tt> before returning to avoid a memory leak.
236
+ <pre><b>
237
+ have = CHUNK - strm.avail_out;
238
+ if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
239
+ (void)deflateEnd(&amp;strm);
240
+ return Z_ERRNO;
241
+ }
242
+ </b></pre>
243
+ The inner <tt>do</tt>-loop is repeated until the last <tt>deflate()</tt> call fails to fill the
244
+ provided output buffer. Then we know that <tt>deflate()</tt> has done as much as it can with
245
+ the provided input, and that all of that input has been consumed. We can then fall out of this
246
+ loop and reuse the input buffer.
247
+ <p>
248
+ The way we tell that <tt>deflate()</tt> has no more output is by seeing that it did not fill
249
+ the output buffer, leaving <tt>avail_out</tt> greater than zero. However suppose that
250
+ <tt>deflate()</tt> has no more output, but just so happened to exactly fill the output buffer!
251
+ <tt>avail_out</tt> is zero, and we can't tell that <tt>deflate()</tt> has done all it can.
252
+ As far as we know, <tt>deflate()</tt>
253
+ has more output for us. So we call it again. But now <tt>deflate()</tt> produces no output
254
+ at all, and <tt>avail_out</tt> remains unchanged as <tt>CHUNK</tt>. That <tt>deflate()</tt> call
255
+ wasn't able to do anything, either consume input or produce output, and so it returns
256
+ <tt>Z_BUF_ERROR</tt>. (See, I told you I'd cover this later.) However this is not a problem at
257
+ all. Now we finally have the desired indication that <tt>deflate()</tt> is really done,
258
+ and so we drop out of the inner loop to provide more input to <tt>deflate()</tt>.
259
+ <p>
260
+ With <tt>flush</tt> set to <tt>Z_FINISH</tt>, this final set of <tt>deflate()</tt> calls will
261
+ complete the output stream. Once that is done, subsequent calls of <tt>deflate()</tt> would return
262
+ <tt>Z_STREAM_ERROR</tt> if the flush parameter is not <tt>Z_FINISH</tt>, and do no more processing
263
+ until the state is reinitialized.
264
+ <p>
265
+ Some applications of <em>zlib</em> have two loops that call <tt>deflate()</tt>
266
+ instead of the single inner loop we have here. The first loop would call
267
+ without flushing and feed all of the data to <tt>deflate()</tt>. The second loop would call
268
+ <tt>deflate()</tt> with no more
269
+ data and the <tt>Z_FINISH</tt> parameter to complete the process. As you can see from this
270
+ example, that can be avoided by simply keeping track of the current flush state.
271
+ <pre><b>
272
+ } while (strm.avail_out == 0);
273
+ assert(strm.avail_in == 0); /* all input will be used */
274
+ </b></pre><!-- -->
275
+ Now we check to see if we have already processed all of the input file. That information was
276
+ saved in the <tt>flush</tt> variable, so we see if that was set to <tt>Z_FINISH</tt>. If so,
277
+ then we're done and we fall out of the outer loop. We're guaranteed to get <tt>Z_STREAM_END</tt>
278
+ from the last <tt>deflate()</tt> call, since we ran it until the last chunk of input was
279
+ consumed and all of the output was generated.
280
+ <pre><b>
281
+ /* done when last data in file processed */
282
+ } while (flush != Z_FINISH);
283
+ assert(ret == Z_STREAM_END); /* stream will be complete */
284
+ </b></pre><!-- -->
285
+ The process is complete, but we still need to deallocate the state to avoid a memory leak
286
+ (or rather more like a memory hemorrhage if you didn't do this). Then
287
+ finally we can return with a happy return value.
288
+ <pre><b>
289
+ /* clean up and return */
290
+ (void)deflateEnd(&amp;strm);
291
+ return Z_OK;
292
+ }
293
+ </b></pre><!-- -->
294
+ Now we do the same thing for decompression in the <tt>inf()</tt> routine. <tt>inf()</tt>
295
+ decompresses what is hopefully a valid <em>zlib</em> stream from the input file and writes the
296
+ uncompressed data to the output file. Much of the discussion above for <tt>def()</tt>
297
+ applies to <tt>inf()</tt> as well, so the discussion here will focus on the differences between
298
+ the two.
299
+ <pre><b>
300
+ /* Decompress from file source to file dest until stream ends or EOF.
301
+ inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be
302
+ allocated for processing, Z_DATA_ERROR if the deflate data is
303
+ invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and
304
+ the version of the library linked do not match, or Z_ERRNO if there
305
+ is an error reading or writing the files. */
306
+ int inf(FILE *source, FILE *dest)
307
+ {
308
+ </b></pre>
309
+ The local variables have the same functionality as they do for <tt>def()</tt>. The
310
+ only difference is that there is no <tt>flush</tt> variable, since <tt>inflate()</tt>
311
+ can tell from the <em>zlib</em> stream itself when the stream is complete.
312
+ <pre><b>
313
+ int ret;
314
+ unsigned have;
315
+ z_stream strm;
316
+ char in[CHUNK];
317
+ char out[CHUNK];
318
+ </b></pre><!-- -->
319
+ The initialization of the state is the same, except that there is no compression level,
320
+ of course, and two more elements of the structure are initialized. <tt>avail_in</tt>
321
+ and <tt>next_in</tt> must be initialized before calling <tt>inflateInit()</tt>. This
322
+ is because the application has the option to provide the start of the zlib stream in
323
+ order for <tt>inflateInit()</tt> to have access to information about the compression
324
+ method to aid in memory allocation. In the current implementation of <em>zlib</em>
325
+ (up through versions 1.2.x), the method-dependent memory allocations are deferred to the first call of
326
+ <tt>inflate()</tt> anyway. However those fields must be initialized since later versions
327
+ of <em>zlib</em> that provide more compression methods may take advantage of this interface.
328
+ In any case, no decompression is performed by <tt>inflateInit()</tt>, so the
329
+ <tt>avail_out</tt> and <tt>next_out</tt> fields do not need to be initialized before calling.
330
+ <p>
331
+ Here <tt>avail_in</tt> is set to zero and <tt>next_in</tt> is set to <tt>Z_NULL</tt> to
332
+ indicate that no input data is being provided.
333
+ <pre><b>
334
+ /* allocate inflate state */
335
+ strm.zalloc = Z_NULL;
336
+ strm.zfree = Z_NULL;
337
+ strm.opaque = Z_NULL;
338
+ strm.avail_in = 0;
339
+ strm.next_in = Z_NULL;
340
+ ret = inflateInit(&amp;strm);
341
+ if (ret != Z_OK)
342
+ return ret;
343
+ </b></pre><!-- -->
344
+ The outer <tt>do</tt>-loop decompresses input until <tt>inflate()</tt> indicates
345
+ that it has reached the end of the compressed data and has produced all of the uncompressed
346
+ output. This is in contrast to <tt>def()</tt> which processes all of the input file.
347
+ If end-of-file is reached before the compressed data self-terminates, then the compressed
348
+ data is incomplete and an error is returned.
349
+ <pre><b>
350
+ /* decompress until deflate stream ends or end of file */
351
+ do {
352
+ </b></pre>
353
+ We read input data and set the <tt>strm</tt> structure accordingly. If we've reached the
354
+ end of the input file, then we leave the outer loop and report an error, since the
355
+ compressed data is incomplete. Note that we may read more data than is eventually consumed
356
+ by <tt>inflate()</tt>, if the input file continues past the <em>zlib</em> stream.
357
+ For applications where <em>zlib</em> streams are embedded in other data, this routine would
358
+ need to be modified to return the unused data, or at least indicate how much of the input
359
+ data was not used, so the application would know where to pick up after the <em>zlib</em> stream.
360
+ <pre><b>
361
+ strm.avail_in = fread(in, 1, CHUNK, source);
362
+ if (ferror(source)) {
363
+ (void)inflateEnd(&amp;strm);
364
+ return Z_ERRNO;
365
+ }
366
+ if (strm.avail_in == 0)
367
+ break;
368
+ strm.next_in = in;
369
+ </b></pre><!-- -->
370
+ The inner <tt>do</tt>-loop has the same function it did in <tt>def()</tt>, which is to
371
+ keep calling <tt>inflate()</tt> until has generated all of the output it can with the
372
+ provided input.
373
+ <pre><b>
374
+ /* run inflate() on input until output buffer not full */
375
+ do {
376
+ </b></pre>
377
+ Just like in <tt>def()</tt>, the same output space is provided for each call of <tt>inflate()</tt>.
378
+ <pre><b>
379
+ strm.avail_out = CHUNK;
380
+ strm.next_out = out;
381
+ </b></pre>
382
+ Now we run the decompression engine itself. There is no need to adjust the flush parameter, since
383
+ the <em>zlib</em> format is self-terminating. The main difference here is that there are
384
+ return values that we need to pay attention to. <tt>Z_DATA_ERROR</tt>
385
+ indicates that <tt>inflate()</tt> detected an error in the <em>zlib</em> compressed data format,
386
+ which means that either the data is not a <em>zlib</em> stream to begin with, or that the data was
387
+ corrupted somewhere along the way since it was compressed. The other error to be processed is
388
+ <tt>Z_MEM_ERROR</tt>, which can occur since memory allocation is deferred until <tt>inflate()</tt>
389
+ needs it, unlike <tt>deflate()</tt>, whose memory is allocated at the start by <tt>deflateInit()</tt>.
390
+ <p>
391
+ Advanced applications may use
392
+ <tt>deflateSetDictionary()</tt> to prime <tt>deflate()</tt> with a set of likely data to improve the
393
+ first 32K or so of compression. This is noted in the <em>zlib</em> header, so <tt>inflate()</tt>
394
+ requests that that dictionary be provided before it can start to decompress. Without the dictionary,
395
+ correct decompression is not possible. For this routine, we have no idea what the dictionary is,
396
+ so the <tt>Z_NEED_DICT</tt> indication is converted to a <tt>Z_DATA_ERROR</tt>.
397
+ <p>
398
+ <tt>inflate()</tt> can also return <tt>Z_STREAM_ERROR</tt>, which should not be possible here,
399
+ but could be checked for as noted above for <tt>def()</tt>. <tt>Z_BUF_ERROR</tt> does not need to be
400
+ checked for here, for the same reasons noted for <tt>def()</tt>. <tt>Z_STREAM_END</tt> will be
401
+ checked for later.
402
+ <pre><b>
403
+ ret = inflate(&amp;strm, Z_NO_FLUSH);
404
+ assert(ret != Z_STREAM_ERROR); /* state not clobbered */
405
+ switch (ret) {
406
+ case Z_NEED_DICT:
407
+ ret = Z_DATA_ERROR; /* and fall through */
408
+ case Z_DATA_ERROR:
409
+ case Z_MEM_ERROR:
410
+ (void)inflateEnd(&amp;strm);
411
+ return ret;
412
+ }
413
+ </b></pre>
414
+ The output of <tt>inflate()</tt> is handled identically to that of <tt>deflate()</tt>.
415
+ <pre><b>
416
+ have = CHUNK - strm.avail_out;
417
+ if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
418
+ (void)inflateEnd(&amp;strm);
419
+ return Z_ERRNO;
420
+ }
421
+ </b></pre>
422
+ The inner <tt>do</tt>-loop ends when <tt>inflate()</tt> has no more output as indicated
423
+ by not filling the output buffer, just as for <tt>deflate()</tt>. In this case, we cannot
424
+ assert that <tt>strm.avail_in</tt> will be zero, since the deflate stream may end before the file
425
+ does.
426
+ <pre><b>
427
+ } while (strm.avail_out == 0);
428
+ </b></pre><!-- -->
429
+ The outer <tt>do</tt>-loop ends when <tt>inflate()</tt> reports that it has reached the
430
+ end of the input <em>zlib</em> stream, has completed the decompression and integrity
431
+ check, and has provided all of the output. This is indicated by the <tt>inflate()</tt>
432
+ return value <tt>Z_STREAM_END</tt>. The inner loop is guaranteed to leave <tt>ret</tt>
433
+ equal to <tt>Z_STREAM_END</tt> if the last chunk of the input file read contained the end
434
+ of the <em>zlib</em> stream. So if the return value is not <tt>Z_STREAM_END</tt>, the
435
+ loop continues to read more input.
436
+ <pre><b>
437
+ /* done when inflate() says it's done */
438
+ } while (ret != Z_STREAM_END);
439
+ </b></pre><!-- -->
440
+ At this point, decompression successfully completed, or we broke out of the loop due to no
441
+ more data being available from the input file. If the last <tt>inflate()</tt> return value
442
+ is not <tt>Z_STREAM_END</tt>, then the <em>zlib</em> stream was incomplete and a data error
443
+ is returned. Otherwise, we return with a happy return value. Of course, <tt>inflateEnd()</tt>
444
+ is called first to avoid a memory leak.
445
+ <pre><b>
446
+ /* clean up and return */
447
+ (void)inflateEnd(&amp;strm);
448
+ return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR;
449
+ }
450
+ </b></pre><!-- -->
451
+ That ends the routines that directly use <em>zlib</em>. The following routines make this
452
+ a command-line program by running data through the above routines from <tt>stdin</tt> to
453
+ <tt>stdout</tt>, and handling any errors reported by <tt>def()</tt> or <tt>inf()</tt>.
454
+ <p>
455
+ <tt>zerr()</tt> is used to interpret the possible error codes from <tt>def()</tt>
456
+ and <tt>inf()</tt>, as detailed in their comments above, and print out an error message.
457
+ Note that these are only a subset of the possible return values from <tt>deflate()</tt>
458
+ and <tt>inflate()</tt>.
459
+ <pre><b>
460
+ /* report a zlib or i/o error */
461
+ void zerr(int ret)
462
+ {
463
+ fputs("zpipe: ", stderr);
464
+ switch (ret) {
465
+ case Z_ERRNO:
466
+ if (ferror(stdin))
467
+ fputs("error reading stdin\n", stderr);
468
+ if (ferror(stdout))
469
+ fputs("error writing stdout\n", stderr);
470
+ break;
471
+ case Z_STREAM_ERROR:
472
+ fputs("invalid compression level\n", stderr);
473
+ break;
474
+ case Z_DATA_ERROR:
475
+ fputs("invalid or incomplete deflate data\n", stderr);
476
+ break;
477
+ case Z_MEM_ERROR:
478
+ fputs("out of memory\n", stderr);
479
+ break;
480
+ case Z_VERSION_ERROR:
481
+ fputs("zlib version mismatch!\n", stderr);
482
+ }
483
+ }
484
+ </b></pre><!-- -->
485
+ Here is the <tt>main()</tt> routine used to test <tt>def()</tt> and <tt>inf()</tt>. The
486
+ <tt>zpipe</tt> command is simply a compression pipe from <tt>stdin</tt> to <tt>stdout</tt>, if
487
+ no arguments are given, or it is a decompression pipe if <tt>zpipe -d</tt> is used. If any other
488
+ arguments are provided, no compression or decompression is performed. Instead a usage
489
+ message is displayed. Examples are <tt>zpipe < foo.txt > foo.txt.z</tt> to compress, and
490
+ <tt>zpipe -d < foo.txt.z > foo.txt</tt> to decompress.
491
+ <pre><b>
492
+ /* compress or decompress from stdin to stdout */
493
+ int main(int argc, char **argv)
494
+ {
495
+ int ret;
496
+
497
+ /* do compression if no arguments */
498
+ if (argc == 1) {
499
+ ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION);
500
+ if (ret != Z_OK)
501
+ zerr(ret);
502
+ return ret;
503
+ }
504
+
505
+ /* do decompression if -d specified */
506
+ else if (argc == 2 &amp;&amp; strcmp(argv[1], "-d") == 0) {
507
+ ret = inf(stdin, stdout);
508
+ if (ret != Z_OK)
509
+ zerr(ret);
510
+ return ret;
511
+ }
512
+
513
+ /* otherwise, report usage */
514
+ else {
515
+ fputs("zpipe usage: zpipe [-d] &lt; source &gt; dest\n", stderr);
516
+ return 1;
517
+ }
518
+ }
519
+ </b></pre>
520
+ <hr>
521
+ <i>Copyright (c) 2004 by Mark Adler<br>Last modified 13 November 2004</i>
522
+ </body>
523
+ </html>