Merge pull request #1572 from JabRef/implement-1356

Implement 1356

Author: lenhard

CHANGELOG.md

@@ -12,7 +12,8 @@ We refer to [GitHub issues](https://github.com/JabRef/jabref/issues) by using `#
 ## [Unreleased]
 
 ### Changed
-- Implemented [#661](https://github.com/JabRef/jabref/issues/661): Introducing a "check for updates" mechanism (manually/automatic at startup)
+- Implemented [#1356](https://github.com/JabRef/jabref/issues/1356): Added a formatter for converting HTML to Unicode
+- Implemented [#661](https://github.com/JabRef/jabref/issues/661): Introducing a "check for updates" mechnism (manually/automatic at startup)
 - [#1485](https://github.com/JabRef/jabref/issues/1485): Biblatex field shorttitle is now exported/imported as standard field ShortTitle to Word bibliography
 - [#1431](https://github.com/JabRef/jabref/issues/1431): Import dialog shows file extensions and filters the view
 - Updated German translation

build.gradle

@@ -103,6 +103,8 @@ dependencies {
 
     compile 'commons-logging:commons-logging:1.2'
 
+    compile 'org.apache.commons:commons-lang3:3.4'
+
     compile 'org.jsoup:jsoup:1.9.2'
     compile 'com.mashape.unirest:unirest-java:1.4.9'
     compile 'info.debatty:java-string-similarity:0.13'

src/main/java/net/sf/jabref/logic/formatter/Formatters.java

@@ -23,6 +23,7 @@
 
 import net.sf.jabref.logic.formatter.bibtexfields.ClearFormatter;
 import net.sf.jabref.logic.formatter.bibtexfields.HtmlToLatexFormatter;
+import net.sf.jabref.logic.formatter.bibtexfields.HtmlToUnicodeFormatter;
 import net.sf.jabref.logic.formatter.bibtexfields.LatexCleanupFormatter;
 import net.sf.jabref.logic.formatter.bibtexfields.NormalizeDateFormatter;
 import net.sf.jabref.logic.formatter.bibtexfields.NormalizeMonthFormatter;
@@ -45,6 +46,7 @@ public class Formatters {
 
     public static final List<Formatter> CONVERTERS = Arrays.asList(
             new HtmlToLatexFormatter(),
+            new HtmlToUnicodeFormatter(),
             new LatexToUnicodeFormatter(),
             new UnicodeToLatexFormatter()
     );

src/main/java/net/sf/jabref/logic/formatter/bibtexfields/HtmlToUnicodeFormatter.java

@@ -0,0 +1,36 @@
+package net.sf.jabref.logic.formatter.bibtexfields;
+
+import net.sf.jabref.logic.formatter.Formatter;
+import net.sf.jabref.logic.l10n.Localization;
+import net.sf.jabref.logic.layout.LayoutFormatter;
+
+import org.apache.commons.lang3.StringEscapeUtils;
+
+public class HtmlToUnicodeFormatter implements LayoutFormatter, Formatter {
+
+    @Override
+    public String getName() {
+        return "HTML to Unicode";
+    }
+
+    @Override
+    public String getKey() {
+        return "html_to_unicode";
+    }
+
+    @Override
+    public String getDescription() {
+        return Localization.lang("Converts HTML code to Unicode.");
+    }
+
+    @Override
+    public String getExampleInput() {
+        return "<b>bread</b> &amp; butter";
+    }
+
+    @Override
+    public String format(String fieldText) {
+        // StringEscapeUtils converts characters and regex kills tags
+        return StringEscapeUtils.unescapeHtml4(fieldText).replaceAll("\\<[^>]*>","");
+    }
+}

src/main/resources/l10n/JabRef_da.properties

@@ -1705,3 +1705,5 @@ The_link_has_been_copied_to_the_clipboard.=
 Online_help_forum=
 
 Custom=
+
+Converts_HTML_code_to_Unicode.=

src/main/resources/l10n/JabRef_de.properties

@@ -2279,6 +2279,7 @@ Changes_the_first_letter_of_all_words_to_capital_case_and_the_remaining_letters_
 Cleans_up_LaTeX_code.=Räumt_LaTeX-Code_auf.
 
 Converts_HTML_code_to_LaTeX_code.=Konvertiere_HTML-Code_in_LaTeX-Code.
+Converts_HTML_code_to_Unicode.=Konvertiere_HTML-Code_in_Unicode.
 Converts_LaTeX_encoding_to_Unicode_characters.=Konvertiere_LaTeX_Kodierung_in_Unicode_Zeichen.
 Converts_Unicode_characters_to_LaTeX_encoding.=Konvertiere_Unicode_Zeichen_in_LaTeX_Kodierung.
 Converts_ordinals_to_LaTeX_superscripts.=Konvertiere_Ordinalzahlen_in_LaTeX_Hochstellung.
@@ -2422,3 +2423,5 @@ The_link_has_been_copied_to_the_clipboard.=Der_Link_wurde_in_die_Zwischenablage_
 Online_help_forum=Online-Hilfeforum
 
 Custom=
+
+

src/main/resources/l10n/JabRef_en.properties

@@ -2148,6 +2148,7 @@ Changes_all_letters_to_upper_case.=Changes_all_letters_to_upper_case.
 Changes_the_first_letter_of_all_words_to_capital_case_and_the_remaining_letters_to_lower_case.=Changes_the_first_letter_of_all_words_to_capital_case_and_the_remaining_letters_to_lower_case.
 Cleans_up_LaTeX_code.=Cleans_up_LaTeX_code.
 Converts_HTML_code_to_LaTeX_code.=Converts_HTML_code_to_LaTeX_code.
+Converts_HTML_code_to_Unicode.=Converts_HTML_code_to_Unicode.
 Converts_LaTeX_encoding_to_Unicode_characters.=Converts_LaTeX_encoding_to_Unicode_characters.
 Converts_Unicode_characters_to_LaTeX_encoding.=Converts_Unicode_characters_to_LaTeX_encoding.
 Converts_ordinals_to_LaTeX_superscripts.=Converts_ordinals_to_LaTeX_superscripts.

src/main/resources/l10n/JabRef_es.properties

@@ -1607,3 +1607,5 @@ The_link_has_been_copied_to_the_clipboard.=
 Online_help_forum=
 
 Custom=
+
+Converts_HTML_code_to_Unicode.=

src/main/resources/l10n/JabRef_fa.properties

@@ -2393,3 +2393,5 @@ The_link_has_been_copied_to_the_clipboard.=
 Online_help_forum=
 
 Custom=
+
+Converts_HTML_code_to_Unicode.=

src/main/resources/l10n/JabRef_fr.properties

@@ -1651,3 +1651,5 @@ The_link_has_been_copied_to_the_clipboard.=Le_lien_a_été_copié_dans_le_presse
 Online_help_forum=
 
 Custom=
+
+Converts_HTML_code_to_Unicode.=