Mediawiki.0001.allow-tilde-in-links.property=true | |
Mediawiki.0002.illegalnames-urldecode.property=false | |
Mediawiki.0003.xmlevents.property=com.atlassian.uwc.converters.xml.DefaultXmlEvents | |
Mediawiki.0003.xml-fragments.property=true | |
Mediawiki.0003.xml-fragments-root.property=html | |
## Html Tidy - Turn this option on to automatically correct malformed html/xml | |
#Mediawiki.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: | |
#Mediawiki.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 false if you do not want the | |
## framework to check if the username is an existing confluence user | |
## Requires UDMF Plugin https://studio.plugins.atlassian.com/wiki/display/udmf | |
## If you need to get rid of user/timestamp macros, but don't want the | |
## user timestamp data actually associated, set userdate-disabled to true | |
#Mediawiki.0004.userdate.class=com.atlassian.uwc.converters.mediawiki.UserDateConverter | |
#Mediawiki.0004.users-must-exist.property=true | |
#Mediawiki.0004.userdate-disabled.property=false | |
Mediawiki.0005.tokenize-math.java-regex-tokenizer=((?s)<math>.*?<\/math>){replace-with}$1 | |
## Hierarchy | |
## If your hierarchy can be represented in the page content, uncomment and | |
## configure the 0006 properties to maintain your hierarchy data. | |
## CONFIGURE: | |
## * content-hierarchy-pattern - this is the regex that will find your hierarchy | |
## data. The contents of group 1 in this regex should list the current pages | |
## ancestors. | |
## * content-hierarchy-pattern-includes-current - | |
## if true, content-hierarchy-pattern will be expected to list the current | |
## page title as well. If false, only the ancestors will be expected. | |
## * content-hierarchy-delim - the delimiter that seperates the ancestors in | |
## the ancestor string found by content-hierarchy-pattern | |
## * content-hierarchy-default-root - The pagename of the parent page for | |
## pages with no ancestor. If blank, or a nonexistant pagename, the page will | |
## be given no parent, ie. will be an orphan page, and sibling to Home | |
## * content-hierarchy-setname - If true, the origtitle data will be used | |
## to set the title. Set to true when setting char encoding. | |
## * remove-content - If you want the hierarchy content to be scrubbed from | |
## the page content, set the regex to the same property as | |
## content-hierarchy-pattern. Remember to leave the {replace-with} at the end. | |
#Mediawiki.0006.switch.hierarchy-builder=UseBuilder | |
#MediaWiki.0006.classname.hierarchy-builder=com.atlassian.uwc.hierarchies.ContentHierarchy | |
#Mediawiki.0006.content-hierarchy-pattern.property=\{orig-title:([^}]*)\} | |
#Mediawiki.0006.content-hierarchy-pattern-includes-current.property=true | |
#Mediawiki.0006.content-hierarchy-delim.property=/ | |
#MediaWiki.0006.content-hierarchy-default-root.property=Home | |
#MediaWiki.0006.content-hierarchy-setname.property=false | |
#MediaWiki.0006.remove-content.java-regex=\{orig-title:([^}]*)\}{replace-with} | |
Mediawiki.0009-escapebraces.class=com.atlassian.uwc.converters.mediawiki.EscapeBracesConverter | |
Mediawiki.0010-win-newline-cleaner.class=com.atlassian.uwc.converters.tikiwiki.WinNewlinesConverter | |
Mediawiki.0014-tokenizedollars.java-regex-tokenizer=([$]){replace-with}$1 | |
## Page Histories - if you exported with page history options turned on, | |
## uncomment and configure these options. See | |
## http://confluence.atlassian.com/display/CONFEXT/UWC+Page+History+Framework | |
#Mediawiki.0050.switch.page-history-preservation=true | |
#Mediawiki.0051.suffix.page-history-preservation=-#.txt | |
## Code, Pre, and Leading Spaces | |
Mediawiki.0090-re_pre.java-regex-tokenizer=\<pre\>((?s).*?)\<\/pre\>{replace-with}{code}$1{code} | |
Mediawiki.0095-re_code.java-regex-tokenizer=\<code\>((?s).*?)\<\/code\>{replace-with}{code}$1{code} | |
## requires the Table of Contents Macro, tested with version 1.4.7, | |
## http://www.randombits.org/display/CONF/Table+of+Contents+Plugin | |
Mediawiki.0100-toc.java-regex=__TOC__{replace-with}{toc:outline=true|printable=false|style=none|indent=20px} | |
Mediawiki.0300-re_bold_italics.java-regex='{5}(.*?)'{5}{replace-with}*_$1_* | |
Mediawiki.0330-multiline-edge1.java-regex=''+\r?\n(=+.*?=+\r?\n)''+{replace-with}$1 | |
Mediawiki.0340-re_multiline.class=com.atlassian.uwc.converters.mediawiki.MultilineBasicConverter | |
Mediawiki.0350-re_bold.java-regex='{3}\s*(.*?)\s*'{3}{replace-with}*$1* | |
Mediawiki.0350-re_italics.java-regex='{2}\s*(.*?)\s*'{2}{replace-with}_$1_ | |
Mediawiki.0355-removehtmlcomments.java-regex=<!--.*?-->{replace-with} | |
## Spans need to be cleared before tables | |
#Mediawiki.0356.span-color.java-regex=<span style=\"color:([^\"]+)\">(.*?)<\/span>{replace-with}{color:$1}$2{color} | |
#Mediawiki.0357.span-clear.java-regex=<span[^>]+>(.*?)<\/span>{replace-with}$1 | |
## Tables | |
## Output can be configured with the tableoutput property. Options are: | |
## "confluence", and "contentformatting" which refer to the default confluence | |
## table syntax and the Content Formatting Plugin's table syntax, respectively | |
## Note: switch the 1509 table parser option, if html tables were used as well | |
#Mediawiki.0359.enforce-table-columns-minimum.class=com.atlassian.uwc.converters.mediawiki.EnforceTableMinimumConverter | |
Mediawiki.0360.tableoutput.property=confluence | |
Mediawiki.0360-re_tables.class=com.atlassian.uwc.converters.mediawiki.TableConverter | |
Mediawiki.0361-cleannestedtables.java-regex=(\{panel\}\s*)\|\\\}{replace-with}$1 | |
Mediawiki.0362-re_noformat.java-regex=<nowiki>((?s).*?)<\/nowiki>{replace-with}{noformat}$1{noformat} | |
Mediawiki.0365.tokenize-exclamation.java-regex-tokenizer=([!]){replace-with}\\! | |
## Handle redirect syntax before link syntax - you'll need to install the | |
## Redirection Plugin to use this converter | |
## http://www.customware.net/repository/display/AtlassianPlugins/Redirection+Plugin | |
#Mediawiki.0368.redirect.class=com.atlassian.uwc.converters.mediawiki.RedirectConverter | |
## NOTE: Images must come after tables or the whitespace gets screwed up if a table has images | |
## Images must come before Links or Alias handling will make Image conversion more complicated | |
Mediawiki.0370-re_images.class=com.atlassian.uwc.converters.mediawiki.ImageConverter | |
Mediawiki.0400-categories2labels.class=com.atlassian.uwc.converters.mediawiki.CategoryConverter | |
Mediawiki.0401-re_links_no_categories.java-regex=((?i)\[\[(category:[^\]]+)\]\]\s*)+{replace-with} | |
Mediawiki.0402-re_bild_to_images.java-regex=(?i)\[\[Bild:\s*([^\]\|\s]+)\s*\]\]{replace-with}!$1! | |
Mediawiki.0402-re_file_to_images.java-regex=(?i)\[\[file:\s*([^\]\|\s]+)\s*\]\]{replace-with}!$1! | |
Mediawiki.0403-re_links_to_images.java-regex=(?i)\[\[:?Media:\s*([^\]]+)\]\]{replace-with}[[^$1]] | |
## 404 and 405 are wikipedia interwiki links. See uwc-296. | |
## Uncomment to have [[wikipedia:tags]] become [tags@wikipedia]. | |
## You'll need to add the appropriate Confluence shortcut link | |
## 404 and 405 must be before the namespace cleaner. | |
#Mediawiki.0404.allow-at-in-links.property=true | |
#Mediawiki.0405.wikipedia.java-regex=\[wikipedia:([^|\]]+){replace-with}[$1@wikipedia | |
Mediawiki.0406-mailto.java-regex=(?i)(?<=\[)(mailto:[^\] ]*) +([^\]]*){replace-with}$2|$1 | |
Mediawiki.0407-re_links_colons.class=com.atlassian.uwc.converters.mediawiki.NamespaceCleaner | |
Mediawiki.0408-re_links-ws1.java-regex=\[\s+([^\]]+?)\]{replace-with}[$1] | |
Mediawiki.0409-re_links-ws2.java-regex=\[([^\]]+?)\s+\]{replace-with}[$1] | |
Mediawiki.0410-re_links.java-regex=\[\[([^|\]]*)\]\]{replace-with}[$1] | |
Mediawiki.0420-re_links_alias.java-regex=\[\[([^|]*)\| *([^\]]*)\]\]{replace-with}[$2|$1] | |
Mediawiki.0421-re_links_ws.java-regex=(\[[^|\]]+\|[^\]]+) (\]){replace-with}$1$2 | |
Mediawiki.0430-re_links_external_alias.java-regex=\[((?:(?:https?)|(?:file)):\/\/\S+) ([^\]]*)\]{replace-with}[$2|$1] | |
Mediawiki.0500-re_h4.java-regex=(?s)={5}\s*(.*?)\s*={5}{replace-with}h4. $1 | |
Mediawiki.0510-re_h3.java-regex=(?s)={4}\s*(.*?)\s*={4}{replace-with}h3. $1 | |
Mediawiki.0520-re_h2.java-regex=(?s)={3}\s*(.*?)\s*={3}{replace-with}h2. $1 | |
Mediawiki.0530-re_h1.java-regex=(?s)={2}\s*(.*?)\s*={2}{replace-with}h1. $1 | |
Mediawiki.0540-re_title.java-regex=(^|\n)={1}([^=]+)={1}(\n|$){replace-with}$1h1. $2$3 | |
#Mediawiki.0710-images_ws2underscore.class=com.atlassian.uwc.converters.mediawiki.ImageWhitespaceConverter | |
## Set the external-internal-links-identifier to your mediawiki's domain, if | |
## your users might have included links to raw internal mediawiki urls | |
## example: [http://mymediawiki.org/index.php/Some_Mediawiki_Page Link] | |
#Mediawiki.0790.external-internal-links.class=com.atlassian.uwc.converters.mediawiki.ExternalInternalLinksConverter | |
#Mediawiki.0790.external-internal-links-identifier.property=https?:\/\/wiki.someplace.com\/ | |
Mediawiki.0800-attachments.class=com.atlassian.uwc.converters.mediawiki.AttachmentConverter | |
Mediawiki.0910-linebreaks.class=com.atlassian.uwc.converters.mediawiki.BreakConverter | |
## Lists | |
Mediawiki.0950-lists.java-regex=(^|\n)([*#]+)([^*#\s])([^*\n]*)(?=\n){replace-with}$1$2 $3$4 | |
Mediawiki.0955-lists-w-bold.java-regex=(^|\n)([*#]*)([*])(\s)([^*\n]*?)( *[*]){replace-with}$1$2$4*$5* | |
Mediawiki.0960-definitionlists.class=com.atlassian.uwc.converters.mediawiki.DefinitionList | |
Mediawiki.0970-indenting.java-regex=(^|\n):+(.*){replace-with}$1$2 | |
## SubPageList3 | |
## If you used the SubPageList3 <splist ...> tag syntax to automatically | |
## list children, uncomment this converter to have them transformed to | |
## confluence children macro | |
#Mediawiki.0980-subpagelist3-children.class=com.atlassian.uwc.converters.mediawiki.SubpagelistConverter | |
## Discussion Pages -> Comments | |
## Use the delim properties to seperate the Discussion page into distinct | |
## comments. Here are 3 examples based on wikipedia discussion pages | |
## Tell the CommentConverter where the Discussion pages are in relation | |
## to the Pages by setting a relative directory in the location property | |
## For more info see UWC Mediawiki Notes - Comments section | |
#Mediawiki.1000.discussionpages2comments.class=com.atlassian.uwc.converters.mediawiki.CommentConverter | |
Mediawiki.1000.discussion-delim-end-1.property=\[\[User.*?UTC\)[^\n]* | |
Mediawiki.1000.discussion-delim-start-2.property=\n[=] | |
Mediawiki.1000.discussion-delim-start-3.property=\n[----] | |
Mediawiki.1000.discussion-location.property=../Discussions/ | |
## Filenames | |
## strip out filename extensions when importing | |
Mediawiki.1010-remove-extension.class=com.atlassian.uwc.converters.ChopPageExtensionsConverter | |
## replace single _ with space | |
Mediawiki.1020-underscore2space.class=com.atlassian.uwc.converters.mediawiki.ConvertUnderscoresInTitle | |
## set this property to true if you want underscores in links to be translated to spaces. See UWC-291 | |
Mediawiki.1021.underscore2space-links.property=false | |
## HTML | |
## HTML: prep for the sax parser | |
Mediawiki.1400.amp-entity.java-regex=[&](?![#a-zA-Z0-9]{2,5};){replace-with}& | |
Mediawiki.1410.tokenize-math-again.java-regex-tokenizer=((?s)<math>.*?<\/math>){replace-with}$1 | |
## HTML: If you are getting sax errors complaining about namespaces that aren't | |
## bound, add converters like 1420 and 1421, to remove refs to them: | |
## where, t = the first letter of the tags that are having the problem | |
## and, x = the namespace that isn't bound | |
## 1420 handles an attribute with no value. Ex: x:abc | |
## 1421 handles an attribute with a value. Ex: x:foo="bar" | |
#Mediawiki.1420.unbound-namespace-noval.java-regex=<(t[^ >]* )[^>]*?x:[^ >]*{replace-with}<$1 | |
#Mediawiki.1421.unbound-namespace-hasval.java-regex=<(t[^ >]* )[^>]*?(x:[^">]*"[^">]*"\s*)+{replace-with}<$1 | |
## Alternative to XmlConverter for some unnested html syntaxes | |
#Mediawiki.1470.optionalunnestedhtml-bold.java-regex=<\/?b>{replace-with}* | |
#Mediawiki.1471.optionalunnestedhtml-ital.java-regex=<\/?i>{replace-with}_ | |
#Mediawiki.1472.optionalunnestedhtml-strike.java-regex=<\/?strike>{replace-with}- | |
#Mediawiki.1473.optionalunnestedhtml-tt.java-regex=<tt>(.*?)</tt>{replace-with}{{$1}} | |
#Mediawiki.1474.optionalunnestedhtml-strong.java-regex=<\/?strong>{replace-with}* | |
#Mediawiki.1475.optionalunnestedhtml-u.java-regex=<\/?u>{replace-with}+ | |
#Mediawiki.1476.optionalunnestedhtml-header.java-regex=<h(\d)>(.*?)</h\d>{replace-with}h$1. $2 | |
#Mediawiki.1477.optionalunnestedhtml-em.java-regex=<\/?em>{replace-with}_ | |
#Mediawiki.1478.optionalunnestedxml-graphiz.java-regex-tokenizer=<\/?graphviz[^>]*>{replace-with}{graphviz} | |
#Mediawiki.1479.optionalunnestedxml-emptycell.java-regex=> (<\/td>){replace-with}> $1 | |
#Mediawiki.1480.optionalunnestedxml-tablenoparams.java-regex=<\/?((?:table)|(?:tr)|(?:td))>{replace-with}{$1} | |
#Mediawiki.1481.optionalunnestedxml-tableparams.class=com.atlassian.uwc.converters.mediawiki.UnnestedTableHtmlParams | |
#Mediawiki.1482.optionalunnestedxml-hidetable.java-regex-tokenizer=(?s)(\{table.*?\{table\}){replace-with}$1 | |
## HTML: set up the parser events | |
Mediawiki.1501.bold.xmlevent={tag}b{class}com.atlassian.uwc.converters.xml.example.BoldParser | |
Mediawiki.1501.strong.xmlevent={tag}strong{class}com.atlassian.uwc.converters.xml.example.BoldParser | |
Mediawiki.1502.italic.xmlevent={tag}i{class}com.atlassian.uwc.converters.xml.ItalicParser | |
Mediawiki.1503.emph.xmlevent={tag}em{class}com.atlassian.uwc.converters.xml.ItalicParser | |
Mediawiki.1504.underline.xmlevent={tag}u{class}com.atlassian.uwc.converters.xml.UnderlineParser | |
Mediawiki.1505.monospace.xmlevent={tag}tt{class}com.atlassian.uwc.converters.xml.MonoParser | |
Mediawiki.1506.header.xmlevent={tag}h1, h2, h3, h4, h5, h6{class}com.atlassian.uwc.converters.xml.HeaderParser | |
Mediawiki.1507.lists.xmlevent={tag}ol,ul,li{class}com.atlassian.uwc.converters.xml.ListParser | |
Mediawiki.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 | |
Mediawiki.1509.table.xmlevent={tag}table,tr,td{class}com.atlassian.uwc.converters.xml.SimpleTableParser | |
#Mediawiki.1509.table.xmlevent={tag}table,tr,td,th{class}com.atlassian.uwc.converters.xml.ContentFormattingTableParser | |
## HTML: Parse the xml document | |
Mediawiki.1590.xmlconverter.class=com.atlassian.uwc.converters.xml.XmlConverter | |
## Leading Spaces -> panel or noformat macros | |
## Set leading-spaces-noformat property to true if you want the output | |
## to be noformat lines instead of one big panel macro. | |
## Note: using noformat will be more effecient | |
## Set the leading-spaces-delim to 'code','noformat', or 'panel'. the noformat | |
## property must be false. Default is panel | |
Mediawiki.1600.leading-spaces-noformat.property=false | |
#Mediawiki.1600.leading-spaces-delim.property=code | |
Mediawiki.1600-ws2panel.class=com.atlassian.uwc.converters.mediawiki.LeadingSpacesConverter | |
## For any tokenizer regex above, strip out tokens | |
Mediawiki.2000-detokenize.class=com.atlassian.uwc.converters.DetokenizerConverter | |
## Do math last, after math tags are detokenized | |
Mediawiki.2100-math.class=com.atlassian.uwc.converters.mediawiki.MathConverter |