dokuwiki, Improved Link handling, Improved Code Block handling (leading spaces)
diff --git a/conf/converter.dokuwiki.properties b/conf/converter.dokuwiki.properties
index 16d5854..dbd9779 100644
--- a/conf/converter.dokuwiki.properties
+++ b/conf/converter.dokuwiki.properties
@@ -45,13 +45,19 @@
## correspond to your pages setting, but with "media" instead of "pages" as the penultimate directory
#DokuWiki.001.attachmentdirectory.property=/Absolute/path/to/media/dir::/Absolute/path/to/media/foo
# Code (needs to be early so we can tokenize the contents)
-DokuWiki.0code.java-regex-tokenizer=(?s)<code>(.*?)<\/code>{replace-with}{code}$1{code}
-DokuWiki.0code-type.java-regex-tokenizer=(?s)\<code ([^>]+?)\>(.*?)<\/code>{replace-with}{code:$1}$2{code}
-DokuWiki.0noformat.java-regex-tokenizer=(?s)%%(.*?)%%{replace-with}{noformat}$1{noformat}
-DokuWiki.0esc-lbrackets.java-regex=(?<!\[)\[(?!\[){replace-with}\\[
-DokuWiki.0esc-lcurlybrace.java-regex=(?<!\{)\{(?!\{){replace-with}\\{
+DokuWiki.002.code.java-regex-tokenizer=(?s)<code>(.*?)<\/code>{replace-with}{code}$1{code}
+DokuWiki.002.code-tsql.java-regex-tokenizer=(?s)\<code (tsql)\>(.*?)<\/code>{replace-with}{code:sql}$2{code}
+DokuWiki.002.code-type.java-regex-tokenizer=(?s)\<code ([^>]+?)\>(.*?)<\/code>{replace-with}{code:$1}$2{code}
+DokuWiki.002.noformat.java-regex-tokenizer=(?s)%%(.*?)%%{replace-with}{noformat}$1{noformat}
+# We do this after code because code blocks often have leading spaces and we
+# don't want to transform a code block more than once
+DokuWiki.003.leadingspacestocode.class=com.atlassian.uwc.converters.dokuwiki.LeadingSpacesConverter
+# We redo this so that the results of leadingspaces are tokenized
+DokuWiki.004.code.java-regex-tokenizer=(?s)<code>(.*?)<\/code>{replace-with}{code}$1{code}
+DokuWiki.009.esc-lbrackets.java-regex=(?<!\[)\[(?!\[){replace-with}\\[
+DokuWiki.009.esc-lcurlybrace.java-regex=(?<!\{)\{(?!\{){replace-with}\\{
## Tag Plugin - https://www.dokuwiki.org/plugin:tag
-DokuWiki.0.tags.class=com.atlassian.uwc.converters.dokuwiki.TagConverter
+DokuWiki.010.tags.class=com.atlassian.uwc.converters.dokuwiki.TagConverter
# Text formating
DokuWiki.1bold.perl=s/\*\*([^*]+?)\*\*/*$1*/g
DokuWiki.1italic.perl=s/(?s)([^:])\/\/(.+?)\/\//$1_$2_/g
@@ -94,7 +100,7 @@
# ====================================================================================================================
# Lists
-DokuWiki.lists.class=com.atlassian.uwc.converters.dokuwiki.ListConverter
+DokuWiki.3.lists.class=com.atlassian.uwc.converters.dokuwiki.ListConverter
# Tables -- must be run before the image and link converters
DokuWiki.21.prep-colspans.class=com.atlassian.uwc.converters.dokuwiki.PrepColSpansConverter
@@ -112,6 +118,8 @@
DokuWiki.3interwiki_wp1.perl=s/\[\[[\\s]*wp>([^\|\]]*)\|([^\]]*)\]/[[http:\/\/en.wikipedia.org\/wiki\/$1|$2]/g
# Match [wp>...]
DokuWiki.3interwiki_wp2.perl=s/\[\[[\\s]*wp>([^\]\|]*)\]/[[http:\/\/en.wikipedia.org\/wiki\/$1|$1]/g
+# Match [[\\some\windows\share]]
+#DokuWiki.3.winshare.java-regex=\[\[(\\\\.*?)\]\]{replace-with}[$1]
## Images
## If using DokuwikiHierarchy, comment DokuWikiImageConverter, and uncomment HierarchyImageConverter
@@ -174,8 +182,10 @@
#DokuWiki.7.userdata.class=com.atlassian.uwc.converters.dokuwiki.DokuwikiUserDate
# Detokenize (code blocks)
-DokuWiki.90.detokenizer.class=com.atlassian.uwc.converters.DetokenizerConverter
+DokuWiki.91.detokenizer.class=com.atlassian.uwc.converters.DetokenizerConverter
+# Tokenize existing html tags
+DokuWiki.92.htmltags.java-regex-tokenizer=(?s)<html>(.*?)</html>{replace-with}$1
# Transform to Confluence XHTML Format as a converter
DokuWiki.95.confluencemarkuptoxhtml.class=com.atlassian.uwc.converters.ConfluenceMarkupToXhtml
# Don't allow the engine to run the transformation
@@ -183,3 +193,10 @@
# Handle Table col and rowspans
DokuWiki.96.table-rowandcolspans.class=com.atlassian.uwc.converters.dokuwiki.TableRowColSpanConverter
+# Detokenize (html tags) - we do this to address cases where the users had
+# Dokuwiki markup and html tagged markup. DokuWiki.92 tokenized the tags before
+# the call to get the atlassian xhtml, but then the tokens were transformed so
+# we have to fix them with 97 and 98 before we can detokenize
+DokuWiki.97.fixtokenizertokens-start.java-regex=<sub>(?=UWCTOKENSTART){replace-with}~
+DokuWiki.98.fixtokenizertokens-end.java-regex=(?<=UWCTOKENEND)</sub>{replace-with}~
+DokuWiki.99.detokenizer.class=com.atlassian.uwc.converters.DetokenizerConverter
diff --git a/sampleData/dokuwiki/confluenceSettings.properties b/sampleData/dokuwiki/confluenceSettings.properties
index 52e7e5e..882022f 100644
--- a/sampleData/dokuwiki/confluenceSettings.properties
+++ b/sampleData/dokuwiki/confluenceSettings.properties
@@ -15,5 +15,4 @@
feedback.option=true
password=admin
wikitype=dokuwiki
-pages=/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/dokuwiki/SampleDokuwiki-InputCode.txt::/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/dokuwiki/SampleDokuwiki-InputDiscussion.txt::/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/dokuwiki/SampleDokuwiki-InputEsc.txt::/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/dokuwiki/SampleDokuwiki-InputExt.txt::/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/dokuwiki/SampleDokuwiki-InputLists.txt::/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/dokuwiki/SampleDokuwiki-InputMailto.txt::/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/dokuwiki/SampleDokuwiki-InputManfred.txt::/Users/laura/Code/Subversion/uwc-spac/devel/sampleData/dokuwiki/SampleDokuwiki-InputOptLink.txt
-#pages=/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputTables.txt
+pages=/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputCode.txt::/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputDiscussion.txt::/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputEsc.txt::/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputExt.txt::/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputLists.txt::/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputMailto.txt::/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputManfred.txt::/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputOptLink.txt::/Users/laura/Code/Git/uwc/sampleData/dokuwiki/SampleDokuwiki-InputTables.txt
diff --git a/sampleData/dokuwiki/junit_resources/meta/foo.meta b/sampleData/dokuwiki/junit_resources/meta/foo.meta
new file mode 100644
index 0000000..5f0e021
--- /dev/null
+++ b/sampleData/dokuwiki/junit_resources/meta/foo.meta
@@ -0,0 +1,2 @@
+a:2:{s:7:"current";a:10:{s:4:"date";a:2:{s:7:"created";i:1317381420;s:8:"modified";i:1321430495;}s:7:"creator";s:13:"Myrna Loy";s:11:"last_change";a:7:{s:4:"date";i:1321430495;s:2:"ip";s:9:"10.1.3.33";s:4:"type";s:1:"E";s:2:"id";s:64:"sampledokuwikiinputtitle";s:4:"user";s:3:"mloy";s:3:"sum";s:29:"";s:5:"extra";s:0:"";}s:11:"contributor";a:2:{s:3:"foo";s:13:"Myrna Loy";s:3:"ast";s:13:"Asta";}s:4:"user";s:0:"";s:5:"title";s:25:"Foo tralala";s:11:"description";a:2:{s:15:"tableofcontents";a:0:{};s:8:"abstract";s:353:"Testing...
+ ";}s:7:"subject";a:0:{};s:8:"internal";a:2:{s:5:"cache";b:1;s:3:"toc";b:1;}s:8:"relation";a:1:{s:10:"firstimage";s:59:"";}}s:10:"persistent";a:5:{s:4:"date";a:2:{s:7:"created";i:1317381420;s:8:"modified";i:1321430495;}s:7:"creator";s:13:"Myrna Loy";s:11:"last_change";a:7:{s:4:"date";i:1321430495;s:2:"ip";s:9:"10.1.3.33";s:4:"type";s:1:"E";s:2:"id";s:64:"";s:4:"user";s:3:"";s:3:"sum";s:29:" ";s:5:"extra";s:0:"";}s:11:"contributor";a:2:{s:3:"ml";s:13:"ML";s:3:"as";s:13:"asta";}s:4:"user";s:0:"";}}
diff --git a/sampleData/dokuwiki/junit_resources/meta/foo/bar.meta b/sampleData/dokuwiki/junit_resources/meta/foo/bar.meta
new file mode 100644
index 0000000..8a3b12c
--- /dev/null
+++ b/sampleData/dokuwiki/junit_resources/meta/foo/bar.meta
@@ -0,0 +1,2 @@
+a:2:{s:7:"current";a:10:{s:4:"date";a:2:{s:7:"created";i:1317381420;s:8:"modified";i:1321430495;}s:7:"creator";s:13:"Myrna Loy";s:11:"last_change";a:7:{s:4:"date";i:1321430495;s:2:"ip";s:9:"10.1.3.33";s:4:"type";s:1:"E";s:2:"id";s:64:"sampledokuwikiinputtitle";s:4:"user";s:3:"mloy";s:3:"sum";s:29:"";s:5:"extra";s:0:"";}s:11:"contributor";a:2:{s:3:"foo";s:13:"Myrna Loy";s:3:"ast";s:13:"Asta";}s:4:"user";s:0:"";s:5:"title";s:25:"Harumph BAr";s:11:"description";a:2:{s:15:"tableofcontents";a:0:{};s:8:"abstract";s:353:"Testing...
+ ";}s:7:"subject";a:0:{};s:8:"internal";a:2:{s:5:"cache";b:1;s:3:"toc";b:1;}s:8:"relation";a:1:{s:10:"firstimage";s:59:"";}}s:10:"persistent";a:5:{s:4:"date";a:2:{s:7:"created";i:1317381420;s:8:"modified";i:1321430495;}s:7:"creator";s:13:"Myrna Loy";s:11:"last_change";a:7:{s:4:"date";i:1321430495;s:2:"ip";s:9:"10.1.3.33";s:4:"type";s:1:"E";s:2:"id";s:64:"";s:4:"user";s:3:"";s:3:"sum";s:29:" ";s:5:"extra";s:0:"";}s:11:"contributor";a:2:{s:3:"ml";s:13:"ML";s:3:"as";s:13:"asta";}s:4:"user";s:0:"";}}
diff --git a/sampleData/dokuwiki/testall.sh b/sampleData/dokuwiki/testall.sh
index b4559ba..4bea6a2 100755
--- a/sampleData/dokuwiki/testall.sh
+++ b/sampleData/dokuwiki/testall.sh
@@ -12,6 +12,9 @@
echo "Lists"
./compare.sh Lists
+echo "Tables"
+./compare.sh Tables
+
## Not completely implemented yet
#echo "Image"
#./compare.sh Image
diff --git a/src/com/atlassian/uwc/converters/LeadingSpacesBaseConverter.java b/src/com/atlassian/uwc/converters/LeadingSpacesBaseConverter.java
new file mode 100644
index 0000000..a3de079
--- /dev/null
+++ b/src/com/atlassian/uwc/converters/LeadingSpacesBaseConverter.java
@@ -0,0 +1,73 @@
+package com.atlassian.uwc.converters;
+
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import com.atlassian.uwc.converters.tikiwiki.RegexUtil;
+import com.atlassian.uwc.ui.Page;
+
+/**
+ * @author Laura Kolker
+ * Utility methods for transforming a syntax that starts each line into a block contained with outer delimiters.
+ * See dokuwiki's LeadingSpacesConverter for example of usage.
+ */
+public abstract class LeadingSpacesBaseConverter extends BaseConverter {
+
+ protected String initialspacedelim = " ";
+ private String newline = "\n";
+ private String noNewlines = "[^\n]+";
+ private String optNoSpace = "([^ ]?)";
+ private String leadingSpaceLine = "(" + initialspacedelim + noNewlines + newline + ")";
+ private String manyLeadingSpaceLines = "(" + leadingSpaceLine + "+)";
+ private String regex = "(?:\n|^)" + manyLeadingSpaceLines + optNoSpace;
+ /**
+ * assumes one leading space. If you want to customize the pattern, use
+ * generateLeadingPattern
+ */
+ protected Pattern leadingSpacesPattern = Pattern.compile(regex);
+
+ public String convertLeadingSpacesReplaceAll(String input, Pattern pattern, String replacement) {
+ try {
+ Matcher m = pattern.matcher(input);
+ if (m.find()) {
+ log.debug("Leading Spaces - regex found: " + m.group());
+ return m.replaceAll(replacement);
+ }
+ } catch (StackOverflowError e) {
+ log.debug("Too much backtracking. Skipping.");
+ }
+ return input;
+ }
+
+ public String convertLeadingSpacesLoop(String input, String regex, String replacement) {
+ return RegexUtil.loopRegex(input, regex, replacement);
+ }
+
+ public String getReplacement(String delim) {
+ return getReplacement(delim, delim);
+ }
+
+ public String getReplacement(String delim, String enddelim) {
+ return "\n" + delim +
+ "\n$1" + enddelim +
+ "\n$3";
+ }
+
+ public String getReplacementLoopUtil(String delim, String enddelim) {
+ return "\n" + delim +
+ "\n{group1}" + enddelim +
+ "\n{group3}";
+ }
+
+ /**
+ * @param initialspacedelim initial ws delimiter that must be present to presume the line
+ * is a leading spaces line
+ * @return
+ */
+ protected String generateLeadingPattern(String initialspacedelim) {
+ String leadingSpaceLine = "(" + initialspacedelim + noNewlines + newline + ")";
+ String manyLeadingSpaceLines = "(" + leadingSpaceLine + "+)";
+ String regex = "(?:\n|^)" + manyLeadingSpaceLines + optNoSpace;
+ return regex;
+ }
+}
diff --git a/src/com/atlassian/uwc/converters/dokuwiki/DokuwikiUserDate.java b/src/com/atlassian/uwc/converters/dokuwiki/DokuwikiUserDate.java
index d541602..95ed00a 100644
--- a/src/com/atlassian/uwc/converters/dokuwiki/DokuwikiUserDate.java
+++ b/src/com/atlassian/uwc/converters/dokuwiki/DokuwikiUserDate.java
@@ -12,12 +12,13 @@
import com.atlassian.uwc.ui.FileUtils;
import com.atlassian.uwc.ui.Page;
-public class DokuwikiUserDate extends BaseConverter {
+public class DokuwikiUserDate extends HierarchyTarget {
Logger log = Logger.getLogger(this.getClass());
public void convert(Page page) {
String changeFilepath = createChangeFilename(page.getFile().getPath());
if (changeFilepath == null) {
+ log.warn("Could not handle user and date data. Check filepath-hierarchy-ignorable-ancestors amd meta-dir settings. Skipping");
return;
}
File changeFile = new File(changeFilepath);
@@ -50,25 +51,7 @@
private String createChangeFilename(String path) {
return getMetaFilename(path, ".changes");
}
- protected String getMetaFilename(String path, String filetype) {
- String metadir = getProperties().getProperty("meta-dir", null);
- if (metadir == null) {
- log.warn("Could not handle user and date data. meta-dir property must be set. Skipping");
- return null;
- }
- String ignorable = getProperties().getProperty("filepath-hierarchy-ignorable-ancestors", null);
- if (ignorable == null) {
- log.warn("Could not handle user and date data. filepath-hierarchy-ignorable-ancestors must be set. Skipping");
- return null;
- }
- String relative = path.replaceFirst("\\Q" + ignorable + "\\E", "");
- relative = relative.replaceFirst("\\.txt$", filetype);
- if (relative.startsWith(File.separator) && metadir.endsWith(File.separator))
- relative = relative.substring(1);
- if (!relative.startsWith(File.separator) && !metadir.endsWith(File.separator))
- relative = File.separator + relative;
- return metadir + relative;
- }
+
Pattern lastline = Pattern.compile("[^\n]*$");
private String getLastLine(String input) {
diff --git a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyLinkConverter.java b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyLinkConverter.java
index f798df9..e8accdb 100644
--- a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyLinkConverter.java
+++ b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyLinkConverter.java
@@ -1,19 +1,22 @@
package com.atlassian.uwc.converters.dokuwiki;
+import java.io.File;
import java.util.HashMap;
import java.util.Vector;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
-import com.atlassian.uwc.converters.IllegalLinkNameConverter;
+import org.apache.log4j.Logger;
+
import com.atlassian.uwc.converters.tikiwiki.RegexUtil;
import com.atlassian.uwc.ui.Page;
public class HierarchyLinkConverter extends HierarchyTarget {
+ Logger log = Logger.getLogger(this.getClass());
public void convert(Page page) {
String input = page.getOriginalText();
- String converted = convertLink(input, getCurrentPath(page), getSpacekey(page));
+ String converted = convertLink(input, getCurrentPath(page), getSpacekey(page), page.getFile().getPath());
page.setConvertedText(converted);
}
@@ -28,9 +31,9 @@
Pattern link = Pattern.compile("(?<=\\[)\\[([^\\]]*)\\](?=\\])");
Pattern onecolon = Pattern.compile("^([^:]*:)([^:]*)$");
protected String convertLink(String input) {
- return convertLink(input, null, getSpacekey(null));
+ return convertLink(input, null, getSpacekey(null), "");
}
- protected String convertLink(String input, String currentPath, String spacekey) {
+ protected String convertLink(String input, String currentPath, String spacekey, String pagepath) {
Matcher linkFinder = link.matcher(input);
String currentSpacekey = spacekey;
Vector<String> allspaces = getSpaces();
@@ -59,30 +62,46 @@
}
if (target.startsWith(":")) target = target.replaceFirst(":", "");
//figure out if we've already got the space represented
- String targetPart1 = target.replaceFirst(":.*$", "");
+ String targetPart1 = target.replaceFirst(":[^:]+$", "");
boolean containsSpace = false;
if (allspaces.contains(targetPart1))
containsSpace = true;
+ log.debug("targetPart1 =" + targetPart1);
//get rid of unnecessary links to start
//(start page content will be moved to parent in DokuwikiHierarchy
//unless the start page is a top level page in the space)
- if (!(containsSpace && (onecolon.matcher(target)).matches()))
+ boolean isOne = (onecolon.matcher(target)).matches();
+ if (!(containsSpace && isOne))
target = target.replaceFirst(":start$", "");
if (containsSpace) //remove the space from the target for now
target = target.replaceFirst("\\Q"+targetPart1+"\\E:", "");
String hierarchy = target; //save for later
+ //is there a meta title to be used?
+// log.debug("pagepath = " + pagepath);
+ String metaFilename = getMetaFilename(pagepath, ".meta");
+// log.debug("isOne = " + isOne + ", target = " + target + ", metaFilename = " + metaFilename);
+ metaFilename = getTargetMetaFilename(target, metaFilename, isOne);
+ log.debug("metaFilename = " + metaFilename);
+ String metatitle = HierarchyTitleConverter.getMetaTitle(metaFilename);
+ log.debug("metatitle = " + metatitle);
//get confluence page name and fix the case to match HierarchyTitleConverter
- target = target.replaceFirst("^.*:", ""); //remove everything to the last colon
+ if (metatitle == null || "".equals(metatitle))
+ target = target.replaceFirst("^.*:", ""); //remove everything to the last colon
+ else //title was set with metadata
+ target = metatitle;
target = HierarchyTitleConverter.casify(target); //foo_bar becomes Foo Bar
//fix collisions
String linkSpacekey = currentSpacekey;
+ targetPart1 = targetPart1.replaceAll(":", File.separator);
+ log.debug("containsSpace: " + containsSpace + ", ns: "+ namespaces.containsKey(targetPart1));
if (!containsSpace && namespaces.containsKey(targetPart1)) {
linkSpacekey = namespaces.get(targetPart1);
}
if (containsSpace) linkSpacekey = targetPart1;
- target = fixCollisions(target, hierarchy, linkSpacekey);
+// target = fixCollisions(target, hierarchy, linkSpacekey);//collisions handling has to happen elsewhere?
//underscores to spaces
target = target.replaceAll("_", " ");
+ log.debug("link target = " + target);
//add spacekey to target if necessary
if (!target.contains(":") || containsSpace)
target = linkSpacekey + ":" + target;
@@ -101,6 +120,33 @@
}
return input;
}
+
+
+ Pattern metaFile = Pattern.compile("([\\\\/])([^\\\\/]+)(\\.meta)$");
+ protected String getTargetMetaFilename(String target, String metaFilename, boolean isOne) {
+ target=target.replaceAll(":+", File.separator);
+ if (!target.startsWith(File.separator)) target = File.separator + target;
+ if (!isOne) {
+ String metadir = getProperties().getProperty("meta-dir", null);
+ return metadir + target + ".meta";
+ }
+ Matcher metaFinder = metaFile.matcher(metaFilename);
+ StringBuffer sb = new StringBuffer();
+ boolean found = false;
+ if (metaFinder.find()) {
+ found = true;
+ String replacement = target + metaFinder.group(3);
+
+ replacement = RegexUtil.handleEscapesInReplacement(replacement);
+ metaFinder.appendReplacement(sb, replacement);
+ }
+ if (found) {
+ metaFinder.appendTail(sb);
+ return sb.toString();
+ }
+ return null;
+ }
+
Pattern protocol = Pattern.compile("(https?:)|(ftp:)");
private boolean isExternal(String target) {
Matcher protocolFinder = protocol.matcher(target);
diff --git a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyLinkConverterTest.java b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyLinkConverterTest.java
index 8df5ef7..79fc7e7 100644
--- a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyLinkConverterTest.java
+++ b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyLinkConverterTest.java
@@ -1,5 +1,7 @@
package com.atlassian.uwc.converters.dokuwiki;
+import java.io.File;
+import java.io.IOException;
import java.util.Properties;
import junit.framework.TestCase;
@@ -7,6 +9,7 @@
import org.apache.log4j.Logger;
import org.apache.log4j.PropertyConfigurator;
+import com.atlassian.uwc.ui.FileUtils;
import com.atlassian.uwc.ui.Page;
public class HierarchyLinkConverterTest extends TestCase {
@@ -26,6 +29,9 @@
props.put("filepath-hierarchy-ext", "");
props.put("filepath-hierarchy-ignorable-ancestors", "sampleData/hierarchy/dokuwiki");
tester.setProperties(props);
+
+ tester.getProperties().setProperty("meta-dir", HierarchyTitleConverterTest.METADIR);
+ tester.getProperties().setProperty("filepath-hierarchy-ignorable-ancestors", HierarchyTitleConverterTest.PAGESDIR);
}
public void testConvertLink() {
@@ -88,7 +94,7 @@
"[Fruit Drink|food:Drink Fruit]\n" +
"[food:Cranberry]";
String spacekey = "food";
- actual = tester.convertLink(input, "drink/", spacekey);
+ actual = tester.convertLink(input, "drink/", spacekey, "");
assertNotNull(actual);
assertEquals(expected, actual);
}
@@ -103,7 +109,7 @@
}
public void testConvertWithPageByPageSpaces() {
- Page page = new Page(null);
+ Page page = new Page(new File(HierarchyTitleConverterTest.PAGESDIR+"/SampleDokuwiki-InputTitle.txt"));
page.setOriginalText("[[.:home]]\n" +
"[[drink:start]]\n");
String spacekey = "otherspace";
@@ -115,4 +121,44 @@
assertNotNull(actual);
assertEquals(expected, actual);
}
+
+ public void testConvertWithMetaTitle() throws IOException {
+ String input, expected, actual;
+ input = "[[.:foo]]\n" +
+ "[[:foo:bar]]\n";
+ expected = "[xyz:Foo Tralala]\n" +
+ "[xyz:Harumph BAr]\n";
+ tester.getProperties().setProperty("filepath-hierarchy-ignorable-ancestors", "/Users/laura/Code/Git/uwc/sampleData/dokuwiki/junit_resources/pages");
+ String pretendthispagepath = "/Users/laura/Code/Git/uwc/sampleData/dokuwiki/junit_resources/pages/test.txt";
+ actual = tester.convertLink(input, "", "xyz", pretendthispagepath);
+ assertNotNull(actual);
+ assertEquals(expected, actual);
+
+ }
+
+ public void testGetTargetMetaFilename() {
+ String input, expected, actual;
+ input = "foo";
+ String filename = HierarchyTitleConverterTest.METADIR+"/home.meta";
+ expected = HierarchyTitleConverterTest.METADIR+"/foo.meta";
+ actual = tester.getTargetMetaFilename(input, filename, true);
+ assertNotNull(actual);
+ assertEquals(expected, actual);
+
+
+ input = "abc:def:ghi::jkl";
+ filename = HierarchyTitleConverterTest.METADIR+"/abc/def/ghi/home.meta";
+ expected = HierarchyTitleConverterTest.METADIR+"/abc/def/ghi/jkl.meta";
+ actual = tester.getTargetMetaFilename(input, filename, false);
+ assertNotNull(actual);
+ assertEquals(expected, actual);
+ }
+
+ public void testConvertWithAnotherSpacekey() {
+ fail();
+ }
+
+ public void testConvertWithCollision() {
+ fail();
+ }
}
diff --git a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTarget.java b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTarget.java
index b7e657b..5ceecfb 100644
--- a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTarget.java
+++ b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTarget.java
@@ -1,5 +1,6 @@
package com.atlassian.uwc.converters.dokuwiki;
+import java.io.File;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Properties;
@@ -88,4 +89,22 @@
return full.replaceAll("\\Q"+ignorable + "\\E", "");
}
+ protected String getMetaFilename(String path, String filetype) {
+ String metadir = getProperties().getProperty("meta-dir", null);
+ if (metadir == null) {
+ return null;
+ }
+ String ignorable = getProperties().getProperty("filepath-hierarchy-ignorable-ancestors", null);
+ if (ignorable == null) {
+ return null;
+ }
+ String relative = path.replaceFirst("\\Q" + ignorable + "\\E", "");
+ relative = relative.replaceFirst("\\.txt$", filetype);
+ if (relative.startsWith(File.separator) && metadir.endsWith(File.separator))
+ relative = relative.substring(1);
+ if (!relative.startsWith(File.separator) && !metadir.endsWith(File.separator))
+ relative = File.separator + relative;
+ return metadir + relative;
+ }
+
}
diff --git a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTitleConverter.java b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTitleConverter.java
index fcdf4d8..bbe0844 100644
--- a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTitleConverter.java
+++ b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTitleConverter.java
@@ -12,7 +12,7 @@
public class HierarchyTitleConverter extends DokuwikiUserDate {
- Logger log = Logger.getLogger(this.getClass());
+ static Logger log = Logger.getLogger(HierarchyTitleConverter.class);
public void convert(Page page) {
String name = page.getName();
//check the metadata for a title
@@ -23,26 +23,32 @@
page.setName(name);
}
- Pattern title = Pattern.compile("s:5:\"title\";" +
+ static Pattern title = Pattern.compile("s:5:\"title\";" +
"s:\\d+:\"(.*?)\";" +
"s:11:\"description\";");
public String getMetaTitle(Page page) {
if (page == null) return page.getName();
if (page.getFile() == null) return page.getName();
String metaFilename = getMetaFilename(page.getFile().getPath(), ".meta");
- if (metaFilename == null) return page.getName();
+ String title = getMetaTitle(metaFilename);
+ if (title == null) return page.getName();
+ return title;
+ }
+
+ public static String getMetaTitle(String metaFilename) {
+ if (metaFilename == null) return null;
String contents = null;
try {
contents = FileUtils.readTextFile(new File(metaFilename));
} catch (IOException e) {
- log.debug("Problem reading meta file: " + metaFilename,e);
- return page.getName();
+ log.debug("Problem reading meta file: " + metaFilename);
+ return null;
}
Matcher titleFinder = title.matcher(contents);
if (titleFinder.find()) {
return titleFinder.group(1);
}
- return page.getName();
+ return null;
}
public static String fixTitle(String name) {
diff --git a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTitleConverterTest.java b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTitleConverterTest.java
index 1389752..b105e6a 100644
--- a/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTitleConverterTest.java
+++ b/src/com/atlassian/uwc/converters/dokuwiki/HierarchyTitleConverterTest.java
@@ -18,9 +18,9 @@
HierarchyTitleConverter tester = null;
Logger log = Logger.getLogger(this.getClass());
- private static final String METADIR = "sampleData/dokuwiki/junit_resources/meta";
+ static final String METADIR = "sampleData/dokuwiki/junit_resources/meta";
private static final String SAMPLEMETA = METADIR + "/SampleDokuwiki-InputTitle.meta";
- private static final String PAGESDIR = "sampleData/dokuwiki/junit_resources/pages";
+ static final String PAGESDIR = "sampleData/dokuwiki/junit_resources/pages";
private static final String SAMPLEPAGE = PAGESDIR+"/SampleDokuwiki-InputTitle.txt";
protected void setUp() throws Exception {
diff --git a/src/com/atlassian/uwc/converters/dokuwiki/LeadingSpacesConverter.java b/src/com/atlassian/uwc/converters/dokuwiki/LeadingSpacesConverter.java
new file mode 100644
index 0000000..5ae7f46
--- /dev/null
+++ b/src/com/atlassian/uwc/converters/dokuwiki/LeadingSpacesConverter.java
@@ -0,0 +1,27 @@
+package com.atlassian.uwc.converters.dokuwiki;
+
+import com.atlassian.uwc.converters.LeadingSpacesBaseConverter;
+import com.atlassian.uwc.ui.Page;
+
+/**
+ * @author Laura Kolker
+ * transforms sets of lines starting with two ws into code blocks
+ */
+public class LeadingSpacesConverter extends LeadingSpacesBaseConverter {
+
+ protected String initialspacedelim = " (?! *?[-*])"; //two spaces!
+
+ @Override
+ public void convert(Page page) {
+ String input = page.getOriginalText();
+ String converted = convertLeadingSpaces(input);
+ page.setConvertedText(converted);
+ }
+
+ protected String convertLeadingSpaces(String input) {
+ String replacement = getReplacementLoopUtil("<code>", "</code>");
+ String regex = generateLeadingPattern(this.initialspacedelim);
+ return convertLeadingSpacesLoop(input, regex, replacement);
+ }
+
+}
diff --git a/src/com/atlassian/uwc/converters/dokuwiki/LeadingSpacesConverterTest.java b/src/com/atlassian/uwc/converters/dokuwiki/LeadingSpacesConverterTest.java
new file mode 100644
index 0000000..e2bc560
--- /dev/null
+++ b/src/com/atlassian/uwc/converters/dokuwiki/LeadingSpacesConverterTest.java
@@ -0,0 +1,86 @@
+package com.atlassian.uwc.converters.dokuwiki;
+
+import junit.framework.TestCase;
+
+import org.apache.log4j.Logger;
+import org.apache.log4j.PropertyConfigurator;
+
+public class LeadingSpacesConverterTest extends TestCase {
+
+ LeadingSpacesConverter tester = null;
+ Logger log = Logger.getLogger(this.getClass());
+ protected void setUp() throws Exception {
+ tester = new LeadingSpacesConverter();
+ PropertyConfigurator.configure("log4j.properties");
+ }
+
+ public void testConvertLeadingSpaces() {
+ String input, expected, actual;
+ input = "testing 123\n" +
+ " needs to be in code block\n" +
+ " this part too\n" +
+ "not in code block\n" +
+ " not a code block2\n" +
+ " but this is!\n" +
+ " tralala\n" +
+ " tralalala\n" +
+ " tra!\n" +
+ "end";
+ expected = "testing 123\n" +
+ "<code>\n" +
+ " needs to be in code block\n" +
+ " this part too\n" +
+ "</code>\n" +
+ "not in code block\n" +
+ " not a code block2\n" +
+ "<code>\n" +
+ " but this is!\n" +
+ " tralala\n" +
+ " tralalala\n" +
+ " tra!\n" +
+ "</code>\n" +
+ "end";
+ actual = tester.convertLeadingSpaces(input);
+ assertNotNull(actual);
+ assertEquals(expected, actual);
+ }
+
+ public void testConvertLeadingSpaces_NotLists() {
+ String input, expected, actual;
+ input = "testing 123\n" +
+ " * this is a list not a code block\n" +
+ " * this part too\n" +
+ "end of list \n";
+ expected = "testing 123\n" +
+ " * this is a list not a code block\n" +
+ " * this part too\n" +
+ "end of list \n";
+ actual = tester.convertLeadingSpaces(input);
+ assertNotNull(actual);
+ assertEquals(expected, actual);
+
+ input = "testing 123\n" +
+ " * this is a list not a code block\n" +
+ " * this part too\n" +
+ "end of list \n";
+ expected = "testing 123\n" +
+ " * this is a list not a code block\n" +
+ " * this part too\n" +
+ "end of list \n";
+ actual = tester.convertLeadingSpaces(input);
+ assertNotNull(actual);
+ assertEquals(expected, actual);
+
+ input = "testing 123\n" +
+ " - this is a list not a code block\n" +
+ " - this part too\n" +
+ "end of list \n";
+ expected = "testing 123\n" +
+ " - this is a list not a code block\n" +
+ " - this part too\n" +
+ "end of list \n";
+ actual = tester.convertLeadingSpaces(input);
+ assertNotNull(actual);
+ assertEquals(expected, actual);
+ }
+}
diff --git a/src/com/atlassian/uwc/converters/mediawiki/LeadingSpacesConverter.java b/src/com/atlassian/uwc/converters/mediawiki/LeadingSpacesConverter.java
index 06634ca..1eea214 100644
--- a/src/com/atlassian/uwc/converters/mediawiki/LeadingSpacesConverter.java
+++ b/src/com/atlassian/uwc/converters/mediawiki/LeadingSpacesConverter.java
@@ -6,6 +6,7 @@
import org.apache.log4j.Logger;
import com.atlassian.uwc.converters.BaseConverter;
+import com.atlassian.uwc.converters.LeadingSpacesBaseConverter;
import com.atlassian.uwc.converters.tikiwiki.RegexUtil;
import com.atlassian.uwc.ui.Page;
@@ -27,21 +28,9 @@
* @author Laura Kolker
*
*/
-public class LeadingSpacesConverter extends BaseConverter {
+public class LeadingSpacesConverter extends LeadingSpacesBaseConverter {
Logger log = Logger.getLogger(this.getClass());
-
- //regex parts
- String newline = "\n";
- String space = " ";
- String noNewlines = "[^\n]+";
- String leadingSpaceLine = "(" + space + noNewlines + newline + ")"; //2nd group
- String manyLeadingSpaceLines = "(" + leadingSpaceLine + "+)"; //1st group
- String optNoSpace = "([^ ]?)"; //3rd group
- //is equivalent to: String regex = "\n(( [^\n]+\n)+)([^ ])?";
- String regex = "(?:\n|^)" + manyLeadingSpaceLines + optNoSpace;
- Pattern p = Pattern.compile(regex);
-
- Pattern leadingspaces = Pattern.compile("" +
+ private Pattern leadingspaces = Pattern.compile("" +
"(?<=\n|^) +[^\n]+");
public void convert(Page page) {
log.debug("Converting Leading Spaces - starting");
@@ -70,29 +59,18 @@
}
else {
log.debug("leading spaces -> panel");
- String replacement = getReplacement(); //newlines were giving me trouble in the properties file
- try {
- Matcher m = p.matcher(input);
- if (m.find()) {
- log.debug("Leading Spaces - regex found: " + m.group());
- converted = m.replaceAll(replacement);
- }
- } catch (StackOverflowError e) {
- log.debug("Too much backtracking. Skipping.");
- return;
- }
+ converted = convertLeadingSpacesReplaceAll(input, leadingSpacesPattern, getReplacement());
}
page.setConvertedText(converted);
log.debug("Converting Leading Spaces - complete");
}
+
private String getReplacement() {
String delim = getProperties().getProperty("leading-spaces-delim", "panel");
log.debug("Leading spaces replacement delim: " + delim);
- return "\n{" + delim +
- "}\n$1{" + delim +
- "}\n$3";
+ return getReplacement("{"+delim+"}");
}
}
diff --git a/src/com/atlassian/uwc/converters/mediawiki/LeadingSpacesConverterTest.java b/src/com/atlassian/uwc/converters/mediawiki/LeadingSpacesConverterTest.java
index c03ba06..ab349ca 100644
--- a/src/com/atlassian/uwc/converters/mediawiki/LeadingSpacesConverterTest.java
+++ b/src/com/atlassian/uwc/converters/mediawiki/LeadingSpacesConverterTest.java
@@ -7,11 +7,12 @@
import org.apache.log4j.Logger;
import org.apache.log4j.PropertyConfigurator;
+import com.atlassian.uwc.converters.LeadingSpacesBaseConverter;
import com.atlassian.uwc.ui.Page;
public class LeadingSpacesConverterTest extends TestCase {
- LeadingSpacesConverter tester = null;
+ LeadingSpacesBaseConverter tester = null;
Logger log = Logger.getLogger(this.getClass());
protected void setUp() throws Exception {
tester = new LeadingSpacesConverter();
