http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test-documents.tgz ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test-documents.tgz b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test-documents.tgz new file mode 100644 index 0000000..baca6bb Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test-documents.tgz differ
http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test-documents.zip ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test-documents.zip b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test-documents.zip new file mode 100644 index 0000000..27d600d Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test-documents.zip differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test7Z_protected_passTika.7z ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test7Z_protected_passTika.7z b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test7Z_protected_passTika.7z new file mode 100644 index 0000000..7b31f92 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/test7Z_protected_passTika.7z differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testARofSND.ar ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testARofSND.ar b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testARofSND.ar new file mode 100644 index 0000000..2bcfdab Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testARofSND.ar differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testARofText.ar ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testARofText.ar b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testARofText.ar new file mode 100644 index 0000000..2f01afe --- /dev/null +++ b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testARofText.ar @@ -0,0 +1,5 @@ +!<arch> +testTXT.txt/ 1262968202 500 500 100644 47 ` +Test d'indexation de Txt +http://www.apache.org + http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testBulletPoints.key ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testBulletPoints.key b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testBulletPoints.key new file mode 100644 index 0000000..f2525c4 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testBulletPoints.key differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testEmbedded.zip ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testEmbedded.zip b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testEmbedded.zip new file mode 100644 index 0000000..1c7c03c Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testEmbedded.zip differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testKeynote.key ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testKeynote.key b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testKeynote.key new file mode 100644 index 0000000..6e0e032 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testKeynote.key differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testMasterSlideTable.key ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testMasterSlideTable.key b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testMasterSlideTable.key new file mode 100644 index 0000000..2627770 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testMasterSlideTable.key differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testNumbers.numbers ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testNumbers.numbers b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testNumbers.numbers new file mode 100644 index 0000000..51360e0 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testNumbers.numbers differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testNumbersCharts.numbers ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testNumbersCharts.numbers b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testNumbersCharts.numbers new file mode 100644 index 0000000..058edea Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testNumbersCharts.numbers differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testOpenOffice2.odt ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testOpenOffice2.odt b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testOpenOffice2.odt new file mode 100644 index 0000000..bc31925 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testOpenOffice2.odt differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPages.pages ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPages.pages b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPages.pages new file mode 100644 index 0000000..9fe1e40 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPages.pages differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesComments.pages ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesComments.pages b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesComments.pages new file mode 100644 index 0000000..d7ff81c Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesComments.pages differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersAlphaLower.pages ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersAlphaLower.pages b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersAlphaLower.pages new file mode 100644 index 0000000..b690101 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersAlphaLower.pages differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersAlphaUpper.pages ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersAlphaUpper.pages b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersAlphaUpper.pages new file mode 100644 index 0000000..7d0caf3 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersAlphaUpper.pages differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersFootnotes.pages ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersFootnotes.pages b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersFootnotes.pages new file mode 100644 index 0000000..cfecc8c Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersFootnotes.pages differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersRomanLower.pages ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersRomanLower.pages b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersRomanLower.pages new file mode 100644 index 0000000..9cc0edf Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersRomanLower.pages differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersRomanUpper.pages ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersRomanUpper.pages b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersRomanUpper.pages new file mode 100644 index 0000000..de97673 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesHeadersFootersRomanUpper.pages differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesLayout.pages ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesLayout.pages b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesLayout.pages new file mode 100644 index 0000000..46d8a40 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesLayout.pages differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesPwdProtected.pages ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesPwdProtected.pages b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesPwdProtected.pages new file mode 100644 index 0000000..788b516 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testPagesPwdProtected.pages differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testSVG.svgz ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testSVG.svgz b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testSVG.svgz new file mode 100644 index 0000000..53b9f26 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testSVG.svgz differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTXT.zlib ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTXT.zlib b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTXT.zlib new file mode 100644 index 0000000..596579c Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTXT.zlib differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTables.key ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTables.key b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTables.key new file mode 100644 index 0000000..7259676 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTables.key differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTextBoxes.key ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTextBoxes.key b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTextBoxes.key new file mode 100644 index 0000000..20e2893 Binary files /dev/null and b/tika-parser-modules/tika-parser-package-module/src/test/resources/test-documents/testTextBoxes.key differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testAnnotations.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testAnnotations.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testAnnotations.pdf new file mode 100644 index 0000000..3c778f7 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testAnnotations.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testExtraSpaces.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testExtraSpaces.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testExtraSpaces.pdf new file mode 100644 index 0000000..604a716 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testExtraSpaces.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testOverlappingText.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testOverlappingText.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testOverlappingText.pdf new file mode 100644 index 0000000..282a1ab Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testOverlappingText.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF-custommetadata.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF-custommetadata.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF-custommetadata.pdf new file mode 100644 index 0000000..7b8d002 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF-custommetadata.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF.pdf new file mode 100644 index 0000000..1f1bcff Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFEmbeddingAndEmbedded.docx ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFEmbeddingAndEmbedded.docx b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFEmbeddingAndEmbedded.docx new file mode 100644 index 0000000..e16bf3c Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFEmbeddingAndEmbedded.docx differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFFileEmbInAnnotation.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFFileEmbInAnnotation.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFFileEmbInAnnotation.pdf new file mode 100644 index 0000000..cea1566 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFFileEmbInAnnotation.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFPackage.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFPackage.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFPackage.pdf new file mode 100644 index 0000000..0cd2d48 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFPackage.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFTripleLangTitle.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFTripleLangTitle.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFTripleLangTitle.pdf new file mode 100644 index 0000000..4b50a73 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFTripleLangTitle.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFTwoTextBoxes.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFTwoTextBoxes.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFTwoTextBoxes.pdf new file mode 100644 index 0000000..f24e9e7 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFTwoTextBoxes.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFVarious.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFVarious.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFVarious.pdf new file mode 100644 index 0000000..b18e2a7 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDFVarious.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_PDFEncodedStringInXMP.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_PDFEncodedStringInXMP.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_PDFEncodedStringInXMP.pdf new file mode 100644 index 0000000..2bc80ef Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_PDFEncodedStringInXMP.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.10.x.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.10.x.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.10.x.pdf new file mode 100644 index 0000000..c84e4cf Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.10.x.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.11.x.PDFA-1b.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.11.x.PDFA-1b.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.11.x.PDFA-1b.pdf new file mode 100644 index 0000000..fce27b1 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.11.x.PDFA-1b.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.4.x.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.4.x.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.4.x.pdf new file mode 100644 index 0000000..cd06817 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.4.x.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.5.x.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.5.x.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.5.x.pdf new file mode 100644 index 0000000..95e2472 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.5.x.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.6.x.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.6.x.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.6.x.pdf new file mode 100644 index 0000000..8adc3d4 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.6.x.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.7.x.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.7.x.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.7.x.pdf new file mode 100644 index 0000000..4dcd93f Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.7.x.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.8.x.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.8.x.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.8.x.pdf new file mode 100644 index 0000000..6aad57a Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.8.x.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.9.x.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.9.x.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.9.x.pdf new file mode 100644 index 0000000..582a2e3 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_Version.9.x.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_acroform3.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_acroform3.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_acroform3.pdf new file mode 100644 index 0000000..b1b2517 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_acroform3.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_bom.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_bom.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_bom.pdf new file mode 100644 index 0000000..3b236e6 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_bom.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_bookmarks.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_bookmarks.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_bookmarks.pdf new file mode 100644 index 0000000..e65be90 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_bookmarks.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_childAttachments.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_childAttachments.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_childAttachments.pdf new file mode 100644 index 0000000..7b2158a Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_childAttachments.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_multiFormatEmbFiles.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_multiFormatEmbFiles.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_multiFormatEmbFiles.pdf new file mode 100644 index 0000000..4b0d002 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_multiFormatEmbFiles.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_no_accessibility_owner_empty.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_no_accessibility_owner_empty.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_no_accessibility_owner_empty.pdf new file mode 100644 index 0000000..83cc228 --- /dev/null +++ b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_no_accessibility_owner_empty.pdf @@ -0,0 +1,87 @@ +%PDF-1.4 +%���� +1 0 obj +<< +/Type /Catalog +/Version /1.4 +/Pages 2 0 R +>> +endobj +2 0 obj +<< +/Type /Pages +/Kids [3 0 R] +/Count 1 +>> +endobj +3 0 obj +<< +/Type /Page +/MediaBox [0.0 0.0 612.0 792.0] +/Parent 2 0 R +/Contents 4 0 R +/Resources 5 0 R +>> +endobj +4 0 obj +<< +/Filter [/FlateDecode] +/Length 6 0 R +>> +stream +K� Z�z&$���8^��"�:�i�����I�%`8etoicz���� [ +endstream +endobj +5 0 obj +<< +/Font 7 0 R +>> +endobj +6 0 obj +50 +endobj +7 0 obj +<< +/F1 8 0 R +>> +endobj +8 0 obj +<< +/Subtype /Type1 +/BaseFont /Helvetica-Bold +/Encoding /WinAnsiEncoding +>> +endobj +9 0 obj +<< +/Filter /Standard +/V 1 +/R 3 +/Length 40 +/P -532 +/O <92EA49CA9DCB5D63ED10DA009E9702A403138C6B0DB22EAD209FC73D70EF86F4> +/U <A82D4E323C8FE41C5571FA0856FFD74128BF4E5E4E758A4164004E56FFFA0108> +>> +endobj +xref +0 10 +0000000000 65535 f +0000000015 00000 n +0000000078 00000 n +0000000135 00000 n +0000000247 00000 n +0000000375 00000 n +0000000408 00000 n +0000000426 00000 n +0000000457 00000 n +0000000547 00000 n +trailer +<< +/Root 1 0 R +/ID [<768A456CFDDEA53BC3965B4569E65812> <768A456CFDDEA53BC3965B4569E65812>] +/Encrypt 9 0 R +/Size 10 +>> +startxref +755 +%%EOF http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_no_accessibility_owner_user.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_no_accessibility_owner_user.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_no_accessibility_owner_user.pdf new file mode 100644 index 0000000..01e40ea --- /dev/null +++ b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_no_accessibility_owner_user.pdf @@ -0,0 +1,87 @@ +%PDF-1.4 +%���� +1 0 obj +<< +/Type /Catalog +/Version /1.4 +/Pages 2 0 R +>> +endobj +2 0 obj +<< +/Type /Pages +/Kids [3 0 R] +/Count 1 +>> +endobj +3 0 obj +<< +/Type /Page +/MediaBox [0.0 0.0 612.0 792.0] +/Parent 2 0 R +/Contents 4 0 R +/Resources 5 0 R +>> +endobj +4 0 obj +<< +/Filter [/FlateDecode] +/Length 6 0 R +>> +stream +4�?$7v�/�=�th�;U0�TdRLG����ZÏ�6a�F���Ã^��D +endstream +endobj +5 0 obj +<< +/Font 7 0 R +>> +endobj +6 0 obj +50 +endobj +7 0 obj +<< +/F1 8 0 R +>> +endobj +8 0 obj +<< +/Subtype /Type1 +/BaseFont /Helvetica-Bold +/Encoding /WinAnsiEncoding +>> +endobj +9 0 obj +<< +/Filter /Standard +/V 1 +/R 3 +/Length 40 +/P -532 +/O <CF2662E6FB01997CC7651E17056D4DFAD2C78DD5F3F4109BDFFB50433BB04670> +/U <D803EA55DA7821D2A297F8A68387DCA028BF4E5E4E758A4164004E56FFFA0108> +>> +endobj +xref +0 10 +0000000000 65535 f +0000000015 00000 n +0000000078 00000 n +0000000135 00000 n +0000000247 00000 n +0000000375 00000 n +0000000408 00000 n +0000000426 00000 n +0000000457 00000 n +0000000547 00000 n +trailer +<< +/Root 1 0 R +/ID [<75DB321CAFE7680CAD6FC09F51F3DDBE> <75DB321CAFE7680CAD6FC09F51F3DDBE>] +/Encrypt 9 0 R +/Size 10 +>> +startxref +755 +%%EOF http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_yes_accessibility_owner_empty.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_yes_accessibility_owner_empty.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_yes_accessibility_owner_empty.pdf new file mode 100644 index 0000000..519b162 --- /dev/null +++ b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_yes_accessibility_owner_empty.pdf @@ -0,0 +1,87 @@ +%PDF-1.4 +%���� +1 0 obj +<< +/Type /Catalog +/Version /1.4 +/Pages 2 0 R +>> +endobj +2 0 obj +<< +/Type /Pages +/Kids [3 0 R] +/Count 1 +>> +endobj +3 0 obj +<< +/Type /Page +/MediaBox [0.0 0.0 612.0 792.0] +/Parent 2 0 R +/Contents 4 0 R +/Resources 5 0 R +>> +endobj +4 0 obj +<< +/Filter [/FlateDecode] +/Length 6 0 R +>> +stream +�B�0 �6�Ym�y��mpne�Ê�Ú��j�W��_WA��D�Y���Vs +endstream +endobj +5 0 obj +<< +/Font 7 0 R +>> +endobj +6 0 obj +50 +endobj +7 0 obj +<< +/F1 8 0 R +>> +endobj +8 0 obj +<< +/Subtype /Type1 +/BaseFont /Helvetica-Bold +/Encoding /WinAnsiEncoding +>> +endobj +9 0 obj +<< +/Filter /Standard +/V 1 +/R 3 +/Length 40 +/P -20 +/O <92EA49CA9DCB5D63ED10DA009E9702A403138C6B0DB22EAD209FC73D70EF86F4> +/U <472263FD2B9B40403473D05A693D8C0428BF4E5E4E758A4164004E56FFFA0108> +>> +endobj +xref +0 10 +0000000000 65535 f +0000000015 00000 n +0000000078 00000 n +0000000135 00000 n +0000000247 00000 n +0000000375 00000 n +0000000408 00000 n +0000000426 00000 n +0000000457 00000 n +0000000547 00000 n +trailer +<< +/Root 1 0 R +/ID [<AFAC4D6B4301475F6B6D846BEACCEA36> <AFAC4D6B4301475F6B6D846BEACCEA36>] +/Encrypt 9 0 R +/Size 10 +>> +startxref +754 +%%EOF http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_yes_accessibility_owner_user.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_yes_accessibility_owner_user.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_yes_accessibility_owner_user.pdf new file mode 100644 index 0000000..aaa6c8f --- /dev/null +++ b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_no_extract_yes_accessibility_owner_user.pdf @@ -0,0 +1,87 @@ +%PDF-1.4 +%���� +1 0 obj +<< +/Type /Catalog +/Version /1.4 +/Pages 2 0 R +>> +endobj +2 0 obj +<< +/Type /Pages +/Kids [3 0 R] +/Count 1 +>> +endobj +3 0 obj +<< +/Type /Page +/MediaBox [0.0 0.0 612.0 792.0] +/Parent 2 0 R +/Contents 4 0 R +/Resources 5 0 R +>> +endobj +4 0 obj +<< +/Filter [/FlateDecode] +/Length 6 0 R +>> +stream +Ä�3�ְ6�f ���6��Ä)FD�x�u��K^,��^Ì�8Q��Q�$J +endstream +endobj +5 0 obj +<< +/Font 7 0 R +>> +endobj +6 0 obj +50 +endobj +7 0 obj +<< +/F1 8 0 R +>> +endobj +8 0 obj +<< +/Subtype /Type1 +/BaseFont /Helvetica-Bold +/Encoding /WinAnsiEncoding +>> +endobj +9 0 obj +<< +/Filter /Standard +/V 1 +/R 3 +/Length 40 +/P -20 +/O <CF2662E6FB01997CC7651E17056D4DFAD2C78DD5F3F4109BDFFB50433BB04670> +/U <067DAA91A1AC99D15ABFA0AD86050F3B28BF4E5E4E758A4164004E56FFFA0108> +>> +endobj +xref +0 10 +0000000000 65535 f +0000000015 00000 n +0000000078 00000 n +0000000135 00000 n +0000000247 00000 n +0000000375 00000 n +0000000408 00000 n +0000000426 00000 n +0000000457 00000 n +0000000547 00000 n +trailer +<< +/Root 1 0 R +/ID [<B8090A679399BCAD86E31DE615910182> <B8090A679399BCAD86E31DE615910182>] +/Encrypt 9 0 R +/Size 10 +>> +startxref +754 +%%EOF http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_protected.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_protected.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_protected.pdf new file mode 100644 index 0000000..371a307 Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_protected.pdf differ http://git-wip-us.apache.org/repos/asf/tika/blob/38916f89/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_twoAuthors.pdf ---------------------------------------------------------------------- diff --git a/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_twoAuthors.pdf b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_twoAuthors.pdf new file mode 100644 index 0000000..6a3d96f Binary files /dev/null and b/tika-parser-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_twoAuthors.pdf differ
