para_test_pdf_ids.ini 14 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157
  1. # """
  2. # Para Test Cases of Sci-Hub
  3. # """
  4. demo_parse_pdf(book_name="scihub/scihub_04600000/libgen.scimag04690000-04690999.zip_10.1016/s0378-4347(98)00269-2") # layout
  5. demo_parse_pdf(book_name="scihub/scihub_18500000/libgen.scimag18539000-18539999.zip_10.1039/c2ob27232f") # layout
  6. demo_parse_pdf(book_name="scihub/scihub_28400000/libgen.scimag28413000-28413999.zip_10.2307/1316224") # layout
  7. demo_parse_pdf(book_name="scihub/scihub_00500000/libgen.scimag00527000-00527999.zip_10.1002/app.25178") # 标题,Done。Layout,TODO。公式替换,TODO。
  8. # """
  9. # FOR TEST : 0115~0119 数据测试
  10. # https://aicarrier.feishu.cn/wiki/PIBKwMja9iBySpkV5Ywcy5zdnFE
  11. demo_parse_pdf(book_name="scihub/scihub_18000000/libgen.scimag18064000-18064999.zip_10.1016/s1385-299x(98)00049-x") # 标题序列。二级标题待识别,TODO。
  12. demo_parse_pdf(book_name="scihub/scihub_24400000/libgen.scimag24401000-24401999.zip_10.1016/j.toxicon.2014.02.018") # 标题序列
  13. demo_parse_pdf(book_name="scihub/scihub_29200000/libgen.scimag29285000-29285999.zip_10.1016/j.tiv.2014.09.004") # 标题序列
  14. demo_parse_pdf(book_name="scihub/scihub_87000000/libgen.scimag87032000-87032999.zip_10.3390/rs13010076") # 标题,问题较多,待处理
  15. demo_parse_pdf(book_name="scihub/scihub_75300000/libgen.scimag75322000-75322999.zip_10.7748/ns2007.05.21.34.35.c4550") # 标题、段落。DONE
  16. demo_parse_pdf(book_name="scihub/scihub_11400000/libgen.scimag11451000-11451999.zip_10.1017/s0009838811000231") # 标题
  17. demo_parse_pdf(book_name="scihub/scihub_23000000/libgen.scimag23039000-23039999.zip_10.1007/s10897-013-9674-3") # 标题
  18. demo_parse_pdf(book_name="scihub/scihub_23400000/libgen.scimag23485000-23485999.zip_10.1016/S0891-5849(13)00133-0") # 标题
  19. demo_parse_pdf(book_name="scihub/scihub_36500000/libgen.scimag36588000-36588999.zip_10.1109/adprl.2014.7010623") # 标题
  20. demo_parse_pdf(book_name="scihub/scihub_47300000/libgen.scimag47374000-47374999.zip_10.1016/B978-0-12-410502-7.00005-3") # 标题
  21. demo_parse_pdf(book_name="scihub/scihub_80300000/libgen.scimag80371000-80371999.zip_10.1097/MJT.0000000000001112") # 标题
  22. demo_parse_pdf(book_name="scihub/scihub_82500000/libgen.scimag82595000-82595999.zip_10.1016/B978-0-12-817752-5.00003-2") # 标题
  23. demo_parse_pdf(book_name="scihub/scihub_01900000/libgen.scimag01914000-01914999.zip_10.1006/ndsh.1998.0025") # 标题。240 pages。DONES
  24. demo_parse_pdf(book_name="scihub/scihub_09700000/libgen.scimag09714000-09714999.zip_10.1111/j.1524-4733.2009.00592_2.x") # 标题。240 pages
  25. demo_parse_pdf(book_name="scihub/scihub_87300000/libgen.scimag87385000-87385999.zip_10.1515/pthp-2020-0016") # 段落切割
  26. demo_parse_pdf(book_name="scihub/scihub_23000000/libgen.scimag23003000-23003999.zip_10.1007/s12264-013-1404-1") # 段落,
  27. demo_parse_pdf(book_name="scihub/scihub_37000000/libgen.scimag37068000-37068999.zip_10.1080/0015587X.1936.9718622") # 跨页段落合并。第二页文字没有出现。
  28. demo_parse_pdf(book_name="scihub/scihub_84500000/libgen.scimag84570000-84570999.zip_10.1017/S0033583520000086") # 分段
  29. # END TEST CASES: 0115~0119 数据测试
  30. # """
  31. demo_parse_pdf(book_name="scihub/scihub_18000000/libgen.scimag18064000-18064999.zip_10.1016/s1385-299x(98)00049-x") # 标题序列。二级标题待识别,TODO。
  32. demo_parse_pdf(book_name="scihub/scihub_24400000/libgen.scimag24401000-24401999.zip_10.1016/j.toxicon.2014.02.018") # 标题序列
  33. demo_parse_pdf(book_name="scihub/scihub_29200000/libgen.scimag29285000-29285999.zip_10.1016/j.tiv.2014.09.004") # 标题序列
  34. demo_parse_pdf(book_name="scihub/scihub_50900000/libgen.scimag50902000-50902999.zip_10.1007/s12274-016-1035-8") # 标题序列
  35. demo_parse_pdf(book_name="scihub/scihub_87000000/libgen.scimag87032000-87032999.zip_10.3390/rs13010076") # 标题,问题较多,待处理
  36. demo_parse_pdf(book_name="scihub/scihub_87000000/libgen.scimag87032000-87032999.zip_10.3390/rs13010076") # 标题,问题较多,待处理
  37. demo_parse_pdf(book_name="scihub/scihub_62600000/libgen.scimag62633000-62633999.zip_10.2169/internalmedicine.54.2755") # 标题、段落。DONE
  38. demo_parse_pdf(book_name="scihub/scihub_75300000/libgen.scimag75322000-75322999.zip_10.7748/ns2007.05.21.34.35.c4550") # 标题、段落。DONE
  39. demo_parse_pdf(book_name="scihub/scihub_11400000/libgen.scimag11451000-11451999.zip_10.1017/s0009838811000231") # 标题
  40. demo_parse_pdf(book_name="scihub/scihub_23000000/libgen.scimag23039000-23039999.zip_10.1007/s10897-013-9674-3") # 标题
  41. demo_parse_pdf(book_name="scihub/scihub_23400000/libgen.scimag23485000-23485999.zip_10.1016/S0891-5849(13)00133-0") # 标题
  42. demo_parse_pdf(book_name="scihub/scihub_36500000/libgen.scimag36588000-36588999.zip_10.1109/adprl.2014.7010623") # 标题
  43. demo_parse_pdf(book_name="scihub/scihub_47300000/libgen.scimag47374000-47374999.zip_10.1016/B978-0-12-410502-7.00005-3") # 标题
  44. demo_parse_pdf(book_name="scihub/scihub_80300000/libgen.scimag80371000-80371999.zip_10.1097/MJT.0000000000001112") # 标题
  45. demo_parse_pdf(book_name="scihub/scihub_82500000/libgen.scimag82595000-82595999.zip_10.1016/B978-0-12-817752-5.00003-2") # 标题
  46. # demo_parse_pdf(book_name="scihub/scihub_01900000/libgen.scimag01914000-01914999.zip_10.1006/ndsh.1998.0025") # 标题。240 pages。DONES
  47. # demo_parse_pdf(book_name="scihub/scihub_09700000/libgen.scimag09714000-09714999.zip_10.1111/j.1524-4733.2009.00592_2.x") # 标题。240 pages
  48. demo_parse_pdf(book_name="scihub/scihub_87300000/libgen.scimag87385000-87385999.zip_10.1515/pthp-2020-0016") # 段落切割
  49. demo_parse_pdf(book_name="scihub/scihub_23000000/libgen.scimag23003000-23003999.zip_10.1007/s12264-013-1404-1") # 段落,
  50. demo_parse_pdf(book_name="scihub/scihub_37000000/libgen.scimag37068000-37068999.zip_10.1080/0015587X.1936.9718622") # 跨页段落合并。第二页文字没有出现。
  51. demo_parse_pdf(book_name="scihub/scihub_84500000/libgen.scimag84570000-84570999.zip_10.1017/S0033583520000086") # 分段
  52. demo_parse_pdf(book_name="scihub/scihub_31800000/libgen.scimag31824000-31824999.zip_10.1109/med.2012.6265668") # 复杂公式
  53. demo_parse_pdf(book_name="scihub/scihub_36800000/libgen.scimag36890000-36890999.zip_10.2514/1.4659") # 标题,公式
  54. demo_parse_pdf(book_name="scihub/scihub_58900000/libgen.scimag58981000-58981999.zip_10.1504/ijep.2014.065921") # 公式
  55. demo_parse_pdf(book_name="scihub/scihub_23900000/libgen.scimag23969000-23969999.zip_10.1016/S0008-4182(06)80004-9") # 判断是否原生文本。DONE
  56. demo_parse_pdf(book_name="scihub/scihub_69400000/libgen.scimag69479000-69479999.zip_10.1002/0470871660.part1") # 段落连接,分隔符。TODO
  57. demo_parse_pdf(book_name="scihub/scihub_38000000/libgen.scimag38025000-38025999.zip_10.1557/JMR.2001.0368") # 标题,标题字体比正文略小。TODO
  58. demo_parse_pdf(book_name="scihub/scihub_12600000/libgen.scimag12683000-12683999.zip_10.1007/s10126-001-0057-7") # one block one line. SKIP
  59. demo_parse_pdf(book_name="scihub/scihub_68900000/libgen.scimag68948000-68948999.zip_10.1002/uog.18760") # # 标题和正文混在一个block内部。SKIP
  60. demo_parse_pdf(book_name="scihub/scihub_09700000/libgen.scimag09782000-09782999.zip_10.1111/j.1540-627x.2006.00176.x") # 标题和正文混在一个block内部。SKIP
  61. demo_parse_pdf(book_name="scihub/scihub_45700000/libgen.scimag45725000-45725999.zip_10.1210/en.2008-1281") # 段落合并。DONE。S3文件失效。
  62. demo_parse_pdf(book_name="scihub/scihub_47200000/libgen.scismag47212000-47212999.zip_10.7589/0090-3558-40.3.579") # 段落合并。DONE。S3文件失效。
  63. demo_parse_pdf(book_name="scihub/scihub_83100000/libgen.scimag83192000-83192999.zip_10.1680/jcoma.20.00045") # 段落合并,标题等。DONE。S3文件失效。
  64. demo_parse_pdf(book_name="scihub/scihub_47200000/libgen.scismag47212000-47212999.zip_10.7589/0090-3558-40.3.579") # 段落合并。DONE
  65. demo_parse_pdf(book_name="scihub/scihub_80800000/libgen.scimag80896000-80896999.zip_10.1080/13552600.2019.1695968") # 跨页合并paragraph。DONE
  66. demo_parse_pdf(book_name="scihub/scihub_59800000/libgen.scimag59898000-59898999.zip_10.1002/0471469572.ch5") # 上一段以结束标点结束时,误合并了第二段。DONE.该PDF存在大量图注干扰正文合并的情况。TODO
  67. demo_parse_pdf(book_name="scihub/scihub_61700000/libgen.scimag61796000-61796999.zip_10.1080/10511970.2016.1162889") # 上一段以结束标点结束时,误合并了第二段。DONE
  68. demo_parse_pdf(book_name="scihub/scihub_54500000/libgen.scimag54597000-54597999.zip_10.1186/s40814-015-0033-z") # DONE
  69. demo_parse_pdf(book_name="scihub/scihub_82000000/libgen.scimag82096000-82096999.zip_10.1016/j.mehy.2020.109851") # 该部分文字被当成页眉页脚删除。SKIP
  70. demo_parse_pdf(book_name="scihub/scihub_84600000/libgen.scimag84652000-84652999.zip_10.1163/1876312x-00001010") # 内容丢失。DONE
  71. demo_parse_pdf(book_name="scihub/scihub_17000000/libgen.scimag17000000-17000999.zip_10.1016/j.pain.2004.06.005") # No19,排查多出空格的情况。DONE
  72. demo_parse_pdf(book_name="scihub/scihub_01500000/libgen.scimag01561000-01561999.zip_10.1002/jmor.10887") # 标题。TODO
  73. demo_parse_pdf(book_name="scihub/scihub_09700000/libgen.scimag09782000-09782999.zip_10.1111/j.1540-627x.2006.00176.x") # 段落合并。TODO
  74. demo_parse_pdf(book_name="scihub/scihub_50900000/libgen.scimag50902000-50902999.zip_10.1007/s12274-016-1035-8") # 段落合并。TODO
  75. demo_parse_pdf(book_name="scihub/scihub_62600000/libgen.scimag62633000-62633999.zip_10.2169/internalmedicine.54.2755") # 段落合并。TODO
  76. demo_parse_pdf(book_name="scihub/scihub_73400000/libgen.scimag73490000-73490999.zip_10.1051/epjconf/201714609022") # 段落合并。TODO
  77. demo_parse_pdf(book_name="scihub/scihub_80100000/libgen.scimag80185000-80185999.zip_10.1353/sib.0.0003") # 段落合并。2006年的论文。PDF格式不规范。问题较多。TODO
  78. demo_parse_pdf(book_name="scihub/scihub_62200000/libgen.scimag62272000-62272999.zip_10.1038/srep31158") # 下一页para blocks为空,导致跨页段落合并失败。DONE
  79. demo_parse_pdf(book_name="scihub/scihub_21100000/libgen.scimag21136000-21136999.zip_10.1080/10407780490277879") # 29. 段落以一个大写字母开头。DONE
  80. demo_parse_pdf(book_name="scihub/scihub_09800000/libgen.scimag09855000-09855999.zip_10.1111/j.1574-0862.2006.00110.x") # 2. DONE
  81. demo_parse_pdf(book_name="scihub/scihub_29400000/libgen.scimag29456000-29456999.zip_10.1177/0883911505049656") # 8,9
  82. demo_parse_pdf(book_name="scihub/scihub_31800000/libgen.scimag31839000-31839999.zip_10.4028/www.scientific.net/jbbte.19.99") # 14
  83. demo_parse_pdf(book_name="scihub/scihub_30200000/libgen.scimag30263000-30263999.zip_10.1081/scc-200036639") # 21
  84. demo_parse_pdf(book_name="scihub/scihub_58800000/libgen.scimag58887000-58887999.zip_10.1097/gme.0b013e3181c17c06") # 30
  85. demo_parse_pdf(book_name="scihub/scihub_09000000/libgen.scimag09082000-09082999.zip_10.1111/j.1365-2222.2010.03605.x") # 31,32
  86. demo_parse_pdf(book_name="scihub/scihub_71200000/libgen.scimag71224000-71224999.zip_10.1038/s41396-018-0231-9") # 34
  87. demo_parse_pdf(book_name="scihub/scihub_24600000/libgen.scimag24665000-24665999.zip_10.1016/S0387-7604(89)80007-5") # 39
  88. # """
  89. # Found by wang zhi
  90. # 2024-1-24
  91. # """
  92. demo_parse_pdf(book_name="scihub/scihub_42100000/libgen.scimag42132000-42132999.zip_10.1080/15205430903457430") # 3
  93. demo_parse_pdf(book_name="scihub/scihub_20000000/libgen.scimag20099000-20099999.zip_10.1016/s0015-0282(02)03774-3") # 4
  94. demo_parse_pdf(book_name="scihub/scihub_64900000/libgen.scimag64993000-64993999.zip_10.1097/SIH.0000000000000179") # 5
  95. demo_parse_pdf(book_name="scihub/scihub_01000000/libgen.scimag01040000-01040999.zip_10.1002/chin.200846224") # 12
  96. demo_parse_pdf(book_name="scihub/scihub_42100000/libgen.scimag42162000-42162999.zip_10.1093/notesj/gjm116") # 13
  97. demo_parse_pdf(book_name="scihub/scihub_73100000/libgen.scimag73198000-73198999.zip_10.1007/978-1-4842-4197-4_4") # 20
  98. demo_parse_pdf(book_name="scihub/scihub_16500000/libgen.scimag16596000-16596999.zip_10.1016/j.febslet.2005.05.011") # 24
  99. demo_parse_pdf(book_name="scihub/scihub_53900000/libgen.scimag53941000-53941999.zip_10.1016/s0264-3707(15)00099-x") # 26
  100. demo_parse_pdf(book_name="scihub/scihub_60800000/libgen.scimag60801000-60801999.zip_10.1680/mpal.2014.167.1.61") # 27
  101. demo_parse_pdf(book_name="scihub/scihub_14100000/libgen.scimag14109000-14109999.zip_10.1016/s0960-9822(00)00772-7") # 32
  102. demo_parse_pdf(book_name="scihub/scihub_76200000/libgen.scimag76297000-76297999.zip_10.4018/jehmc.2011040101") # 33
  103. demo_parse_pdf(book_name="scihub/scihub_77600000/libgen.scimag77607000-77607999.zip_10.1016/j.nut.2019.08.013") # 40
  104. demo_parse_pdf(book_name="scihub/scihub_82100000/libgen.scimag82168000-82168999.zip_10.1061/(ASCE)SU.1943-5428.0000323") # 42
  105. # """
  106. # 跨页合并段落多出文字问题
  107. # """
  108. demo_parse_pdf(book_name="scihub/scihub_48600000/libgen.scimag48645000-48645999.zip_10.1163/22941932-90000220") # wang zhi, 31。DONE
  109. demo_parse_pdf(book_name="scihub/scihub_09000000/libgen.scimag09082000-09082999.zip_10.1111/j.1365-2222.2010.03605.x") # xiang, 32
  110. demo_parse_pdf(book_name="scihub/scihub_09800000/libgen.scimag09855000-09855999.zip_10.1111/j.1574-0862.2006.00110.x") # wang zhi, 18。DONE
  111. demo_parse_pdf(book_name="scihub/scihub_76200000/libgen.scimag76297000-76297999.zip_10.4018/jehmc.2011040101") # xiang, 4,5,6。 DONE
  112. # """
  113. # 内容丢失问题
  114. # """
  115. # """
  116. # 标题丢失
  117. # """
  118. demo_parse_pdf(book_name="scihub/scihub_31800000/libgen.scimag31824000-31824999.zip_10.1109/med.2012.6265668") # xiang. 被text_block_horizontal_overlap规则drop.
  119. demo_parse_pdf(book_name="scihub/scihub_01800000/libgen.scimag01870000-01870999.zip_10.1006/jcis.2000.7105") # wangzhi, 1-24, 67. 内容缺失,丢失内容 "thus, there is a". Checking...
  120. demo_parse_pdf(book_name="scihub/") #
  121. # """
  122. # Found by Liu Silu
  123. # 2024-02-04
  124. # """
  125. demo_parse_pdf(book_name="scihub/scihub_38900000/libgen.scimag38917000-38917999.zip_10.1142/S0219649208002159") #
  126. demo_parse_pdf(book_name="scihub/") #