conf/converter.jive.properties - universal-wiki-converter - Git at Google

 Jive.0001.encoding.property=utf-8
 Jive.0002.nocomment.filter=com.atlassian.uwc.converters.jive.filters.NoCommentFilter
 ## Exclude documents that came from user containers.
 #Jive.0002.onlyblogsfromusercontainer.filter=com.atlassian.uwc.converters.jive.filters.UserContainerFilter
 ## Exclude or Include pages based on tags
 ## filterbytag-includeregex : if used, only pages with tags that match the include filter will be allowed. This is a global property and will be applied on all pages.
 ## filterbytag-excluderegex : if used, only pages with tags that do not match the exclude filter will be allowed. This is a global property and will be applied on all pages.
 ## filterbytag-includeregex-SPACEKEY : if used, pages that have this spacekey (as set in the spacemap properties below) will use this include filter in place of the global filter. It acts as an override filter. So if both are in place, this one takes precedence.
 ## filterbytag-excluderegex-SPACEKEY : if used, pages that have this spacekey (as set in the spacemap properties below) will use this exclude filter in place of the global filter. It acts as an override filter. So if both are in place, this one takes precedence.
 ## NOTE: You can have either a global include or global exclude filter or neither, and for any space you can have either an include or exclude filter. If you do not have a global filter, you can still have a space override filter.
 ## NOTE: Spacekeys as defined in the spacemap and in these filter properties will be case sensitive, so make certain they are the same.
 #Jive.0002.filterbytag.filter=com.atlassian.uwc.converters.jive.filters.TagFilter
 #Jive.0002.filterbytag-includeregex.property=^migrate$
 #Jive.0002.filterbytag-excluderegex.property=exclude
 #Jive.0002.filterbytag-includeregex-SPACEKEY.property=^overrideinclude$
 #Jive.0002.filterbytag-excluderegex-testconf.property=^overrideexclude$
 Jive.0003.xmlevents.property=com.atlassian.uwc.converters.xml.DefaultXmlEvents
 Jive.0003.xml-fragments.property=true
 Jive.0003.xml-fragments-root.property=html
 ## Html Tidy - Turn this option on to automatically correct malformed html/xml
 Jive.0003.xml-use-htmltidy.property=true
 ## Html Tidy Options
 ##           - set JTidy options using the following naming convention:
 ##           - xml-tidyopt-key.property=val
 ##           - where key is any supported JTidy key listed here:
 ##             http://www.docjar.com/docs/api/org/w3c/tidy/Tidy.html
 ##             but using the property naming convention listed here:
 ##             http://tidy.sourceforge.net/docs/quickref.html
 ##           - and value is one of the options described here:
 ##             http://tidy.sourceforge.net/docs/quickref.html
 ##           - Example. To turn on numeric-entities, uncomment:
 Jive.0003.xml-tidyopt-numeric-entities.property=true
 ## User Date Metadata - Uncomment these if you want the UWC to convert
 ## optionally exportable user and timestamp metadata
 ## change the users-must-exist property to true if you want the
 ## framework to check if the username is an existing confluence user before
 ## setting the metadata.
 ## Requires UDMF Plugin https://studio.plugins.atlassian.com/wiki/display/udmf
 Jive.0004.userdate.class=com.atlassian.uwc.converters.jive.UserDateConverter
 Jive.0004.users-must-exist.property=false
 ## Repeated basic tags
 Jive.0050.emrepeat.java-regex=(<em>\s*){2,}{replace-with}$1
 Jive.0051.prerepeat.java-regex=(<pre[^>]*>\s*){2,}{replace-with}$1
 Jive.0052.strongrepeat.java-regex=(<strong>\s*){2,}{replace-with}$1
 Jive.0053.emrepeatend.java-regex=(<\/em>\s*){2,}{replace-with}$1
 Jive.0054.prerepeatend.java-regex=(<\/pre>\s*){2,}{replace-with}$1
 Jive.0055.strongrepeatend.java-regex=(<\/strong>\s*){2,}{replace-with}$1
 ## Lots of different pre and CDATA and code syntaxes
 Jive.0090-re_pre.class=com.atlassian.uwc.converters.jive.PreConverter
 Jive.0095-re_code.java-regex-tokenizer=(?s)<code>(.*?)<\/code>{replace-with}{code}$1{code}
 Jive.0096-re_code.java-regex-tokenizer=(?s)([{]code[^}]*[}].*?[{]code[}]){replace-with}$1
 ## Title
 Jive.0200.title.class=com.atlassian.uwc.converters.jive.TitleConverter
 ## Escape brackets -- after tokenizing code blocks, and title handling.
 ##							 And before we make links
 Jive.0210.escapebrackets.java-regex=([\[\]]){replace-with}\\$1
 ## Detect blogs
 Jive.0225.blog.class=com.atlassian.uwc.converters.jive.BlogConverter
 ## Space
 Jive.0250.space.class=com.atlassian.uwc.converters.jive.SpaceConverter
 Jive.0250.spacemap-200-600.property=testconf
 Jive.0250.spacemap-201-14.property=testconf2
 Jive.0250.spacemap-202-14.property=testconf3
 Jive.0250.spacedata.property=/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/jive/junit_resources/exported_jive_containerdata.txt
 ## Comments
 Jive.0275.comment.class=com.atlassian.uwc.converters.jive.CommentConverter
 ## Tags
 Jive.0300.tags.class=com.atlassian.uwc.converters.jive.TagConverter
 ## Table of Contents. Must be handled before images
 Jive.0410.toc.java-regex-tokenizer=<((img)|(span)) __jive_macro_name=.toc.[^>]*?((\/>)|(><\/span>)){replace-with}{toc}
 ## Images - doing this with regex as no nesting and simpler.
 ## handles the inline image syntax and links to attachments
 ## requires attachmentdata property below
 Jive.0450.image.class=com.atlassian.uwc.converters.jive.ImageConverter
 ## Attachments - attaches the files to the page
 Jive.0500.attachments.class=com.atlassian.uwc.converters.jive.AttachmentConverter
 Jive.0500.attachmentdata.property=/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/jive/junit_resources/exported_jive_attachments.txt
 ## Url report 2, needs to be before we remove metadata. Optional. Provides
 ## a before/after report of where a jive page ended up in confluence
 #Jive.0590.urlreport2.class=com.atlassian.uwc.converters.jive.UrlReport2
 ## Remove metadata - Wait to do this until after space, blog, tags, comments,
 ## and attachments have been handled. also urlreport2
 Jive.0600.removemetadata.java-regex=\{jive-export-meta.*?\}{replace-with}
 Jive.0601.removeuserimtestamp.java-regex=\{user[^}]*\}{replace-with}
 Jive.0602.removeuserimtestamp.java-regex=\{timestamp[^}]*\}{replace-with}
 Jive.0603.removetag.java-regex=\{tags:[^}]*\}{replace-with}
 Jive.0604.removeextranl.java-regex=(?m)\n{2,}{replace-with}
 ## Syntaxes that should be run before the XmlConverter
 ## Escape Braces - needs to be run _after_ we've removed the metadata syntax
 ## also after we've tokenized code and pre blocks. Any macros that have to be
 ## handled before this (like toc) will need to be tokenized.
 Jive.0700.escapebraces.java-regex=([{}]){replace-with}\\$1
 # Internal Links - should be after attachment handling
 Jive.0730.internaljivelink.class=com.atlassian.uwc.converters.jive.InternalLinkConverter
 Jive.0730.internaljivedomain.property=http://wiki.abc.com
 Jive.0730.targetconfdomain.property=http://confluence.abc.com
 Jive.0730.titledata.property=/path/to/titledata/set/from/exported/output/properties
 Jive.0800.cleantable.java-regex=<(\/?)table[^>]*>{replace-with}<$1table>
 Jive.0801.cleantable.java-regex=<(\/?)tr[^>]*>{replace-with}<$1tr>
 Jive.0802.cleantable.java-regex=<(\/?)td[^>]*>{replace-with}<$1td>
 Jive.0803.cleantable.java-regex=<(\/?)th[^>]*>{replace-with}<$1th>
 ## HTML: prep for the sax parser
 Jive.1400.amp-entity.java-regex=[&](?![#a-zA-Z0-9]{2,5};){replace-with}&amp;
 Jive.1450.break.java-regex=<br\/?>{replace-with}NEWLINE
 ## Optional: Any pages having parsing errors because of non-html xml tags
 ## that weren't protected by pre blocks? Uncomment this converter and replace
 ## "customtag" with the names of your tags
 #Jive.1455.rawnonhtmlxml.java-regex=<((custom)|(nonhtml)|(xml)|(tag))>{replace-with}&lt;$1&gt;
 Jive.1501.basic.xmlevent={tag}b,i,strong,em,u,s,blockquote,br{class}com.atlassian.uwc.converters.xml.BasicParser
 Jive.1505.monospace.xmlevent={tag}tt{class}com.atlassian.uwc.converters.xml.MonoParser
 Jive.1506.header.xmlevent={tag}h1, h2, h3, h4, h5, h6{class}com.atlassian.uwc.converters.xml.HeaderParser
 Jive.1507.lists.xmlevent={tag}ol,ul,li{class}com.atlassian.uwc.converters.xml.ListParser
 Jive.1508.horizrule.xmlevent={tag}hr{class}com.atlassian.uwc.converters.xml.HorizRuleParser
 ## If you want confluence tables output, use SimpleTableParser, or if you
 ## want content formatting plugin output, use ContentFormattingTableParser
 #Jive.1509.table.xmlevent={tag}table,tr,td{class}com.atlassian.uwc.converters.xml.SimpleTableParser
 Jive.1509.table.xmlevent={tag}table,tr,td,th{class}com.atlassian.uwc.converters.xml.ContentFormattingTableParser
 Jive.1510.para.xmlevent={tag}p{class}com.atlassian.uwc.converters.xml.BreakParser
 Jive.1511.link.xmlevent={tag}a{class}com.atlassian.uwc.converters.xml.LinkParser
 ## HTML: Parse the xml document
 Jive.1585.prepnotext.java-regex=^\s*${replace-with}<body><p/></body>
 Jive.1590.xmlconverter.class=com.atlassian.uwc.converters.xml.XmlConverter
 ## Post XmlConverter processing
 #Jive.1600.addtableclass.java-regex=\{table[^}]+\}{replace-with}{table:class=mig-table}
 ## For any tokenizer regex above, strip out tokens
 Jive.2000-detokenize.class=com.atlassian.uwc.converters.DetokenizerConverter
	Jive.0001.encoding.property=utf-8
	Jive.0002.nocomment.filter=com.atlassian.uwc.converters.jive.filters.NoCommentFilter
	## Exclude documents that came from user containers.
	#Jive.0002.onlyblogsfromusercontainer.filter=com.atlassian.uwc.converters.jive.filters.UserContainerFilter
	## Exclude or Include pages based on tags
	## filterbytag-includeregex : if used, only pages with tags that match the include filter will be allowed. This is a global property and will be applied on all pages.
	## filterbytag-excluderegex : if used, only pages with tags that do not match the exclude filter will be allowed. This is a global property and will be applied on all pages.
	## filterbytag-includeregex-SPACEKEY : if used, pages that have this spacekey (as set in the spacemap properties below) will use this include filter in place of the global filter. It acts as an override filter. So if both are in place, this one takes precedence.
	## filterbytag-excluderegex-SPACEKEY : if used, pages that have this spacekey (as set in the spacemap properties below) will use this exclude filter in place of the global filter. It acts as an override filter. So if both are in place, this one takes precedence.
	## NOTE: You can have either a global include or global exclude filter or neither, and for any space you can have either an include or exclude filter. If you do not have a global filter, you can still have a space override filter.
	## NOTE: Spacekeys as defined in the spacemap and in these filter properties will be case sensitive, so make certain they are the same.
	#Jive.0002.filterbytag.filter=com.atlassian.uwc.converters.jive.filters.TagFilter
	#Jive.0002.filterbytag-includeregex.property=^migrate$
	#Jive.0002.filterbytag-excluderegex.property=exclude
	#Jive.0002.filterbytag-includeregex-SPACEKEY.property=^overrideinclude$
	#Jive.0002.filterbytag-excluderegex-testconf.property=^overrideexclude$
	Jive.0003.xmlevents.property=com.atlassian.uwc.converters.xml.DefaultXmlEvents
	Jive.0003.xml-fragments.property=true
	Jive.0003.xml-fragments-root.property=html
	## Html Tidy - Turn this option on to automatically correct malformed html/xml
	Jive.0003.xml-use-htmltidy.property=true
	## Html Tidy Options
	## - set JTidy options using the following naming convention:
	## - xml-tidyopt-key.property=val
	## - where key is any supported JTidy key listed here:
	## http://www.docjar.com/docs/api/org/w3c/tidy/Tidy.html
	## but using the property naming convention listed here:
	## http://tidy.sourceforge.net/docs/quickref.html
	## - and value is one of the options described here:
	## http://tidy.sourceforge.net/docs/quickref.html
	## - Example. To turn on numeric-entities, uncomment:
	Jive.0003.xml-tidyopt-numeric-entities.property=true
	## User Date Metadata - Uncomment these if you want the UWC to convert
	## optionally exportable user and timestamp metadata
	## change the users-must-exist property to true if you want the
	## framework to check if the username is an existing confluence user before
	## setting the metadata.
	## Requires UDMF Plugin https://studio.plugins.atlassian.com/wiki/display/udmf
	Jive.0004.userdate.class=com.atlassian.uwc.converters.jive.UserDateConverter
	Jive.0004.users-must-exist.property=false
	## Repeated basic tags
	Jive.0050.emrepeat.java-regex=(<em>\s*){2,}{replace-with}$1
	Jive.0051.prerepeat.java-regex=(<pre[^>]>\s){2,}{replace-with}$1
	Jive.0052.strongrepeat.java-regex=(<strong>\s*){2,}{replace-with}$1
	Jive.0053.emrepeatend.java-regex=(<\/em>\s*){2,}{replace-with}$1
	Jive.0054.prerepeatend.java-regex=(<\/pre>\s*){2,}{replace-with}$1
	Jive.0055.strongrepeatend.java-regex=(<\/strong>\s*){2,}{replace-with}$1
	## Lots of different pre and CDATA and code syntaxes
	Jive.0090-re_pre.class=com.atlassian.uwc.converters.jive.PreConverter
	Jive.0095-re_code.java-regex-tokenizer=(?s)<code>(.*?)<\/code>{replace-with}{code}$1{code}
	Jive.0096-re_code.java-regex-tokenizer=(?s)([{]code[^}][}].?[{]code[}]){replace-with}$1
	## Title
	Jive.0200.title.class=com.atlassian.uwc.converters.jive.TitleConverter
	## Escape brackets -- after tokenizing code blocks, and title handling.
	## And before we make links
	Jive.0210.escapebrackets.java-regex=([\[\]]){replace-with}\\$1
	## Detect blogs
	Jive.0225.blog.class=com.atlassian.uwc.converters.jive.BlogConverter
	## Space
	Jive.0250.space.class=com.atlassian.uwc.converters.jive.SpaceConverter
	Jive.0250.spacemap-200-600.property=testconf
	Jive.0250.spacemap-201-14.property=testconf2
	Jive.0250.spacemap-202-14.property=testconf3
	Jive.0250.spacedata.property=/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/jive/junit_resources/exported_jive_containerdata.txt
	## Comments
	Jive.0275.comment.class=com.atlassian.uwc.converters.jive.CommentConverter
	## Tags
	Jive.0300.tags.class=com.atlassian.uwc.converters.jive.TagConverter
	## Table of Contents. Must be handled before images
	Jive.0410.toc.java-regex-tokenizer=<((img)\|(span)) __jive_macro_name=.toc.[^>]*?((\/>)\|(><\/span>)){replace-with}{toc}
	## Images - doing this with regex as no nesting and simpler.
	## handles the inline image syntax and links to attachments
	## requires attachmentdata property below
	Jive.0450.image.class=com.atlassian.uwc.converters.jive.ImageConverter
	## Attachments - attaches the files to the page
	Jive.0500.attachments.class=com.atlassian.uwc.converters.jive.AttachmentConverter
	Jive.0500.attachmentdata.property=/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/jive/junit_resources/exported_jive_attachments.txt
	## Url report 2, needs to be before we remove metadata. Optional. Provides
	## a before/after report of where a jive page ended up in confluence
	#Jive.0590.urlreport2.class=com.atlassian.uwc.converters.jive.UrlReport2
	## Remove metadata - Wait to do this until after space, blog, tags, comments,
	## and attachments have been handled. also urlreport2
	Jive.0600.removemetadata.java-regex=\{jive-export-meta.*?\}{replace-with}
	Jive.0601.removeuserimtestamp.java-regex=\{user[^}]*\}{replace-with}
	Jive.0602.removeuserimtestamp.java-regex=\{timestamp[^}]*\}{replace-with}
	Jive.0603.removetag.java-regex=\{tags:[^}]*\}{replace-with}
	Jive.0604.removeextranl.java-regex=(?m)\n{2,}{replace-with}
	## Syntaxes that should be run before the XmlConverter
	## Escape Braces - needs to be run _after_ we've removed the metadata syntax
	## also after we've tokenized code and pre blocks. Any macros that have to be
	## handled before this (like toc) will need to be tokenized.
	Jive.0700.escapebraces.java-regex=([{}]){replace-with}\\$1
	# Internal Links - should be after attachment handling
	Jive.0730.internaljivelink.class=com.atlassian.uwc.converters.jive.InternalLinkConverter
	Jive.0730.internaljivedomain.property=http://wiki.abc.com
	Jive.0730.targetconfdomain.property=http://confluence.abc.com
	Jive.0730.titledata.property=/path/to/titledata/set/from/exported/output/properties
	Jive.0800.cleantable.java-regex=<(\/?)table[^>]*>{replace-with}<$1table>
	Jive.0801.cleantable.java-regex=<(\/?)tr[^>]*>{replace-with}<$1tr>
	Jive.0802.cleantable.java-regex=<(\/?)td[^>]*>{replace-with}<$1td>
	Jive.0803.cleantable.java-regex=<(\/?)th[^>]*>{replace-with}<$1th>
	## HTML: prep for the sax parser
	Jive.1400.amp-entity.java-regex=[&](?![#a-zA-Z0-9]{2,5};){replace-with}&
	Jive.1450.break.java-regex=<br\/?>{replace-with}NEWLINE
	## Optional: Any pages having parsing errors because of non-html xml tags
	## that weren't protected by pre blocks? Uncomment this converter and replace
	## "customtag" with the names of your tags
	#Jive.1455.rawnonhtmlxml.java-regex=<((custom)\|(nonhtml)\|(xml)\|(tag))>{replace-with}<$1>
	Jive.1501.basic.xmlevent={tag}b,i,strong,em,u,s,blockquote,br{class}com.atlassian.uwc.converters.xml.BasicParser
	Jive.1505.monospace.xmlevent={tag}tt{class}com.atlassian.uwc.converters.xml.MonoParser
	Jive.1506.header.xmlevent={tag}h1, h2, h3, h4, h5, h6{class}com.atlassian.uwc.converters.xml.HeaderParser
	Jive.1507.lists.xmlevent={tag}ol,ul,li{class}com.atlassian.uwc.converters.xml.ListParser
	Jive.1508.horizrule.xmlevent={tag}hr{class}com.atlassian.uwc.converters.xml.HorizRuleParser
	## If you want confluence tables output, use SimpleTableParser, or if you
	## want content formatting plugin output, use ContentFormattingTableParser
	#Jive.1509.table.xmlevent={tag}table,tr,td{class}com.atlassian.uwc.converters.xml.SimpleTableParser
	Jive.1509.table.xmlevent={tag}table,tr,td,th{class}com.atlassian.uwc.converters.xml.ContentFormattingTableParser
	Jive.1510.para.xmlevent={tag}p{class}com.atlassian.uwc.converters.xml.BreakParser
	Jive.1511.link.xmlevent={tag}a{class}com.atlassian.uwc.converters.xml.LinkParser
	## HTML: Parse the xml document
	Jive.1585.prepnotext.java-regex=^\s*${replace-with}<body><p/></body>
	Jive.1590.xmlconverter.class=com.atlassian.uwc.converters.xml.XmlConverter
	## Post XmlConverter processing
	#Jive.1600.addtableclass.java-regex=\{table[^}]+\}{replace-with}{table:class=mig-table}
	## For any tokenizer regex above, strip out tokens
	Jive.2000-detokenize.class=com.atlassian.uwc.converters.DetokenizerConverter