internal xslt: support multiple archive members containing metadata or body text. Apply to indexing openxml foot/endnotes

This commit is contained in:
Jean-Francois Dockes
2020-04-22 14:04:20 +02:00
parent ad03540394
commit 19149020e3
6 changed files with 288 additions and 159 deletions
+98 -58
View File
@@ -46,109 +46,149 @@ application/x-lzma = uncompress python rcluncomp.py 7z %f %t
# A different format (ie text/plain), and a character set can be defined for
# each filter, see the exemples below (ie: msword)
[index]
application/msword = execm python rcldoc.py
application/vnd.ms-excel = execm python rclxls.py
application/vnd.ms-outlook = execm python rclpst.py
application/vnd.ms-powerpoint = execm python rclppt.py
application/pdf = execm python rclpdf.py
application/x-hwp = execm python rclhwp.py
application/vnd.oasis.opendocument.text = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.oasis.opendocument.text-template = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.oasis.opendocument.presentation = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.oasis.opendocument.spreadsheet = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.oasis.opendocument.graphics = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.calc = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.calc.template = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.draw = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.draw.template = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.impress = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.impress.template = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.math = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.writer = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.writer.global = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.sun.xml.writer.template = internal xsltproc meta.xml opendoc-meta.xsl content.xml opendoc-body.xsl
application/vnd.wordperfect = exec wpd/wpd2html;mimetype=text/html
application/x-abiword = internal xsltproc abiword.xsl
text/x-fictionbook = internal xsltproc fb2.xsl
application/vnd.openxmlformats-officedocument.wordprocessingml.document = \
internal xsltproc docProps/core.xml openxml-meta.xsl word/document.xml openxml-word-body.xsl
application/vnd.openxmlformats-officedocument.wordprocessingml.template = \
internal xsltproc docProps/core.xml openxml-meta.xsl word/document.xml openxml-word-body.xsl
application/vnd.openxmlformats-officedocument.presentationml.template = \
execm python rclopxml.py
application/vnd.openxmlformats-officedocument.presentationml.presentation = \
execm python rclopxml.py
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet = \
internal xsltproc docProps/core.xml openxml-meta.xsl xl/sharedStrings.xml openxml-xls-body.xsl
application/vnd.openxmlformats-officedocument.spreadsheetml.template =\
internal xsltproc docProps/core.xml openxml-meta.xsl xl/sharedStrings.xml openxml-xls-body.xsl
application/epub+zip = execm python rclepub
# Returned by xdg-mime for .js. Future-proofing
application/javascript = internal text/plain
# Also Handle the mime type returned by "file -i" for a suffix-less word
# file. This could probably just as well be an excel file, but we have to
# chose one.
application/vnd.ms-office = execm python rcldoc.py
application/vnd.ms-outlook = execm python rclpst.py
application/vnd.oasis.opendocument.text = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.oasis.opendocument.text-template = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.oasis.opendocument.presentation = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.oasis.opendocument.spreadsheet = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.oasis.opendocument.graphics = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.oasis.opendocument.presentation-flat-xml = \
internal xsltproc opendoc-flat.xsl
application/vnd.oasis.opendocument.text-flat-xml = \
internal xsltproc opendoc-flat.xsl
application/vnd.oasis.opendocument.spreadsheet-flat-xml = \
internal xsltproc opendoc-flat.xsl
application/vnd.openxmlformats-officedocument.wordprocessingml.document = \
internal xsltproc meta docProps/core.xml openxml-meta.xsl \
body word/document.xml openxml-word-body.xsl \
body word/footnotes.xml openxml-word-body.xsl \
body word/endnotes.xml openxml-word-body.xsl
application/vnd.openxmlformats-officedocument.wordprocessingml.template = \
internal xsltproc meta docProps/core.xml openxml-meta.xsl \
body word/document.xml openxml-word-body.xsl \
body word/footnotes.xml openxml-word-body.xsl \
body word/endnotes.xml openxml-word-body.xsl
application/vnd.openxmlformats-officedocument.presentationml.template = \
execm python rclopxml.py
application/vnd.openxmlformats-officedocument.presentationml.presentation = \
execm python rclopxml.py
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet = \
internal xsltproc meta docProps/core.xml openxml-meta.xsl \
body xl/sharedStrings.xml openxml-xls-body.xsl
application/vnd.openxmlformats-officedocument.spreadsheetml.template =\
internal xsltproc meta docProps/core.xml openxml-meta.xsl \
body xl/sharedStrings.xml openxml-xls-body.xsl
application/vnd.sun.xml.calc = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.sun.xml.calc.template = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.sun.xml.draw = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.sun.xml.draw.template = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.sun.xml.impress = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.sun.xml.impress.template = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.sun.xml.math = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.sun.xml.writer = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.sun.xml.writer.global = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
application/vnd.sun.xml.writer.template = \
internal xsltproc meta meta.xml opendoc-meta.xsl \
body content.xml opendoc-body.xsl
#application/postscript = exec rclps
#application/x-gnuinfo = execm python rclinfo
#application/x-tar = execm python rcltar
application/epub+zip = execm python rclepub
application/javascript = internal text/plain
application/ogg = execm python rclaudio
application/pdf = execm python rclpdf.py
application/sql = internal text/plain
application/vnd.wordperfect = exec wpd/wpd2html;mimetype=text/html
application/x-7z-compressed = execm python rcl7z
application/x-abiword = internal xsltproc abiword.xsl
application/x-awk = internal text/plain
application/x-chm = execm python rclchm
application/x-dia-diagram = execm python rcldia;mimetype=text/plain
application/x-flac = execm python rclaudio
application/x-gnote = execm python rclxml.py
#application/x-gnuinfo = execm python rclinfo
application/x-hwp = execm python rclhwp.py
application/x-mimehtml = internal message/rfc822
application/x-perl = internal text/plain
application/x-php = internal text/plain
application/x-rar = execm python rclrar;charset=default
application/x-shellscript = internal text/plain
#application/x-tar = execm python rcltar
application/x-webarchive = execm python rclwar
application/x-7z-compressed = execm python rcl7z
application/x-zerosize = internal
application/zip = execm python rclzip;charset=default
audio/mpeg = execm python rclaudio
audio/mp4 = execm python rclaudio
audio/aac = execm python rclaudio
audio/mp4 = execm python rclaudio
audio/mpeg = execm python rclaudio
audio/x-karaoke = execm python rclkar
image/gif = execm rclimg.exe
image/jp2 = execm rclimg.exe
image/jpeg = execm rclimg.exe
image/png = execm rclimg.exe
image/tiff = execm rclimg.exe
image/svg+xml = internal xsltproc svg.xsl
#image/x-xcf = execm rclimg.exe
image/tiff = execm rclimg.exe
inode/symlink = internal
application/x-zerosize = internal
inode/x-empty = internal application/x-zerosize
message/rfc822 = internal
text/calendar = execm python rclics;mimetype=text/plain
text/css = internal text/plain
text/html = internal
text/plain = internal
text/rtf = exec unrtf --nopict --html;mimetype=text/html
#text/rtf = execm python rclrtf.py
text/rtf = exec unrtf --nopict --html;mimetype=text/html
text/x-c = internal
text/x-c++ = internal
text/x-c+ = internal
text/x-csharp = internal text/plain
text/css = internal text/plain
application/javascript = internal text/plain
text/x-csv = internal text/plain
text/x-c++ = internal
text/x-chm-html = internal text/html
text/x-csharp = internal text/plain
text/x-csv = internal text/plain
text/x-fictionbook = internal xsltproc fb2.xsl
text/x-ini = internal text/plain
text/x-mail = internal
text/x-perl = internal text/plain
text/x-python = exec python rclpython
text/x-shellscript = internal text/plain
text/x-srt = internal text/plain
image/x-xcf = execm rclimg.exe
# Generic XML is best indexed as text, else it generates too many errors
# All parameter and tag names, attribute values etc, are indexed as