X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Futil%2FParseHtmlBodyAndLinks.java;h=6713bbca047aad2aba25903dc590f19884c57a23;hb=c2ab85e25d124ad2dc0a6961cd2c5325c27bfa75;hp=19726b90971a0b29fa929f0076bb755f1b3cd7db;hpb=ad15cff29620f960119f80176f1fd443da9f6763;p=jalview.git diff --git a/src/jalview/util/ParseHtmlBodyAndLinks.java b/src/jalview/util/ParseHtmlBodyAndLinks.java index 19726b9..6713bbc 100644 --- a/src/jalview/util/ParseHtmlBodyAndLinks.java +++ b/src/jalview/util/ParseHtmlBodyAndLinks.java @@ -21,6 +21,7 @@ package jalview.util; import java.util.ArrayList; +import java.util.List; import java.util.StringTokenizer; import java.util.regex.Pattern; @@ -32,6 +33,9 @@ import java.util.regex.Pattern; */ public class ParseHtmlBodyAndLinks { + private static final Pattern LEFT_ANGLE_BRACKET_PATTERN = Pattern + .compile("<"); + String orig = null; public String getOrig() @@ -49,9 +53,9 @@ public class ParseHtmlBodyAndLinks return htmlContent; } - ArrayList links = new ArrayList(); + List links = new ArrayList(); - StringBuffer sb = new StringBuffer(); + String content; /** * result of parsing description - with or without HTML tags @@ -61,7 +65,7 @@ public class ParseHtmlBodyAndLinks public String getContent() { - return sb.toString(); + return content; } /** @@ -69,12 +73,19 @@ public class ParseHtmlBodyAndLinks * * @return */ - public ArrayList getLinks() + public List getLinks() { return links; } /** + * Parses the given html and + *
    + *
  • extracts any 'href' links to a list of "displayName|url" strings, + * retrievable by #getLinks
    • + *
  • extracts the remaining text (with %LINK% placeholders replacing hrefs), + * retrievable by #getContent
    • + *
* * @param description * - html or text content to be parsed @@ -91,6 +102,7 @@ public class ParseHtmlBodyAndLinks htmlContent = false; return; } + StringBuilder sb = new StringBuilder(description.length()); if (description.toUpperCase().indexOf("") == -1) { htmlContent = false; @@ -102,7 +114,7 @@ public class ParseHtmlBodyAndLinks String tag = null; while (st.hasMoreElements()) { - token = st.nextToken("&>"); + token = st.nextToken(">"); if (token.equalsIgnoreCase("html") || token.startsWith("/")) { continue; @@ -132,18 +144,6 @@ public class ParseHtmlBodyAndLinks { sb.append(newline); } - else if (token.startsWith("lt;")) - { - sb.append("<" + token.substring(3)); - } - else if (token.startsWith("gt;")) - { - sb.append(">" + token.substring(3)); - } - else if (token.startsWith("amp;")) - { - sb.append("&" + token.substring(4)); - } else { sb.append(token); @@ -153,11 +153,18 @@ public class ParseHtmlBodyAndLinks { // instead of parsing the html into plaintext // clean the description ready for embedding in html - sb = new StringBuffer(Pattern.compile("<").matcher(description) + sb = new StringBuilder(LEFT_ANGLE_BRACKET_PATTERN.matcher(description) .replaceAll("<")); - } + content = translateEntities(sb.toString()); + } + private String translateEntities(String s) + { + s = s.replaceAll("&", "&"); + s = s.replaceAll("<", "<"); + s = s.replaceAll(">", ">"); + return s; } /** @@ -168,7 +175,7 @@ public class ParseHtmlBodyAndLinks */ public String getNonHtmlContent() { - return isHtmlContent() ? sb.toString() : orig; + return isHtmlContent() ? content : orig; } }