Examples of PageElementTag

Examples of org.wikipediacleaner.api.data.PageElementTag

50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
      return false;
    }
    String contents = analysis.getContents();
    int level = 0;
    boolean result = false;
    PageElementTag level0Tag = null;
    int tagIndex = 0;
    while (tagIndex < tags.size()) {
      PageElementTag tag = tags.get(tagIndex);
      tagIndex++;

      if (tag.isFullTag()) {
        // Full tag
        if (level > 0) {
          if (errors == null) {
            return true;
          }
          result = true;
          CheckErrorResult errorResult = createCheckErrorResult(
              analysis,
              tag.getBeginIndex(), tag.getEndIndex());
          errorResult.addReplacement("");
          errors.add(errorResult);
        }
      } else if (tag.isEndTag()) {
        // Closing tag
        level--;
        if (level < 0) {
          level = 0;
          if (errors == null) {
            return true;
          }
          result = true;
          CheckErrorResult errorResult = createCheckErrorResult(
              analysis,
              tag.getBeginIndex(), tag.getEndIndex());
          errorResult.addReplacement("");
          errors.add(errorResult);
        }
      } else {
        if (level == 0) {
          level0Tag = tag;
        } else if (level > 0) {
          if (errors == null) {
            return true;
          }
          result = true;

          // Manage double small tags on the same text
          boolean doubleSmall = false;
          if ((tag.getMatchingTag() != null) &&
              (level0Tag != null) &&
              (level0Tag.getMatchingTag() != null)) {
            if ((level0Tag.getEndIndex() == tag.getBeginIndex()) &&
                (tag.getMatchingTag().getEndIndex() == level0Tag.getMatchingTag().getBeginIndex())) {
              doubleSmall = true;
            }
          }

          if (level0Tag != null) {
            int possibleEnd = getPossibleEnd(analysis, level0Tag);
            if (possibleEnd > 0) {
              CheckErrorResult errorResult = createCheckErrorResult(
                  analysis,
                  level0Tag.getBeginIndex(), possibleEnd,
                  ErrorLevel.WARNING);
              errorResult.addReplacement(
                  contents.substring(level0Tag.getBeginIndex(), possibleEnd) + "</small>",
                  "<small>...</small>");
              errors.add(errorResult);
            } else {
              CheckErrorResult errorResult = createCheckErrorResult(
                  analysis,
                  level0Tag.getBeginIndex(),
                  level0Tag.getEndIndex(),
                  ErrorLevel.CORRECT);
              errors.add(errorResult);
              if (level0Tag.getMatchingTag() != null) {
                errorResult = createCheckErrorResult(
                    analysis,
                    level0Tag.getMatchingTag().getBeginIndex(),
                    level0Tag.getMatchingTag().getEndIndex(),
                    ErrorLevel.CORRECT);
                errors.add(errorResult);
              }
            }
            level0Tag = null;
          }

          int possibleEnd = getPossibleEnd(analysis, tag);
          if (possibleEnd > 0) {
            CheckErrorResult errorResult = createCheckErrorResult(
                analysis, tag.getBeginIndex(), possibleEnd);
            errorResult.addReplacement(
                contents.substring(tag.getBeginIndex(), possibleEnd) + "</small>",
                "<small>...</small>");
            errors.add(errorResult);
          } else {
            CheckErrorResult errorResult = createCheckErrorResult(
                analysis,
                tag.getCompleteBeginIndex(),
                tag.getCompleteEndIndex());
            if (doubleSmall) {
              errorResult.addReplacement(
                  contents.substring(tag.getEndIndex(), tag.getMatchingTag().getBeginIndex()),
                  GT._("Remove <small> tags"));
            }
            if (!tag.isComplete() && !tag.isFullTag() && !tag.isEndTag()) {
              errorResult.addReplacement(
                  PageElementTag.createTag(PageElementTag.TAG_HTML_SMALL, true, false));
            }
            errors.add(errorResult);
            if (tag.isComplete()) {
              tagIndex = PageElementTag.getMatchingTagIndex(tags, tagIndex);
            }
          }
        }
        level++;
View Full Code Here

Examples of org.wikipediacleaner.api.data.PageElementTag

614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
    String contents = analysis.getContents();
    List<PageElementTag> tags = analysis.getCompleteTags(PageElementTag.TAG_WIKI_GALLERY);
    for (PageElementTag tag : tags) {
      removeArea(chunks, tag.getBeginIndex(), tag.getEndIndex());
      if (tag.isComplete() && !tag.isEndTag() && (tag.getMatchingTag() != null)) {
        PageElementTag endTag = tag.getMatchingTag();
        int beginIndex = tag.getEndIndex();
        int tmpIndex = beginIndex;
        while (tmpIndex <= endTag.getBeginIndex()) {
          if ((tmpIndex == endTag.getBeginIndex()) ||
              (contents.charAt(tmpIndex) == '\n')) {
            String line = contents.substring(beginIndex, tmpIndex).trim();
            int colonIndex = line.indexOf(':');
            if ((colonIndex > 0) && (imageNamespace.isPossibleName(line.substring(0, colonIndex)))) {
              int pipeIndex = line.indexOf('|', colonIndex);
              if (pipeIndex < 0) {
                removeArea(chunks, beginIndex, tmpIndex + 1);
              } else {
                removeArea(chunks, beginIndex, beginIndex + pipeIndex + 1);
              }
            } else {
              removeArea(chunks, beginIndex, tmpIndex + 1);
            }
            beginIndex = tmpIndex + 1;
          }
          tmpIndex++;
        }
        removeArea(chunks, endTag.getBeginIndex(), endTag.getEndIndex());
      }
    }
  }
View Full Code Here

Examples of org.wikipediacleaner.api.data.PageElementTag

88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
          while ((currentPos > beginLineIndex) &&
                 (Character.isWhitespace(contents.charAt(currentPos)))) {
            currentPos--;
          }
          if (contents.charAt(currentPos) == '>') {
            PageElementTag tag = analysis.isInTag(currentPos);
            if (tag != null) {
              String name = tag.getNormalizedName();
              if (PageElementTag.TAG_HTML_BR.equals(name)) {
                breakFound = true;
                shouldStop = false;
                beginError = tag.getBeginIndex();
                currentPos = beginError - 1;
              } else if (!breakFound) {
                /*if (PageElementTag.TAG_WIKI_MATH.equals(name)) {
                  tagAfter = true;
                  shouldStop = false;
View Full Code Here

Examples of org.wikipediacleaner.api.data.PageElementTag

48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
    List<PageElementTag> galleryTags = analysis.getCompleteTags(PageElementTag.TAG_WIKI_GALLERY);
    String contents = analysis.getContents();
    boolean result = false;
    for (PageElementTag galleryTag : galleryTags) {
      if (galleryTag.getMatchingTag() != null) {
        PageElementTag endTag = galleryTag.getMatchingTag();
        int beginIndex = galleryTag.getEndIndex();
        int tmpIndex = beginIndex;
        while (tmpIndex <= endTag.getBeginIndex()) {
          if ((tmpIndex == endTag.getBeginIndex()) ||
              (contents.charAt(tmpIndex) == '\n')) {
            String line = contents.substring(beginIndex, tmpIndex).trim();
            int colonIndex = line.indexOf(':');
            if ((colonIndex > 0) && (imageNamespace.isPossibleName(line.substring(0, colonIndex)))) {
              int pipeIndex = line.indexOf('|', colonIndex);
View Full Code Here

Examples of org.wikipediacleaner.api.data.PageElementTag

92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
    int maxTags = tags.size();
    while (tagIndex < maxTags) {

      // Group tags separated only by punctuation characters
      int firstTagIndex = tagIndex;
      PageElementTag firstTag = tags.get(firstTagIndex);
      int lastTagIndex = PageElementTag.groupTags(tags, firstTagIndex, contents, ",;.\'", separator);
      PageElementTag lastTag = tags.get(lastTagIndex);
      tagIndex = lastTagIndex + 1;

      // Remove possible whitespace characters before first reference
      int tmpIndex = firstTag.getBeginIndex() - 1;
      while ((tmpIndex >= 0) &&
             (Character.isWhitespace(contents.charAt(tmpIndex)))) {
        tmpIndex--;
      }

      // Check if previous character is a punctuation
      boolean punctuationFoundBefore = false;
      boolean punctuationFoundBetween = false;
      char punctuation = ' ';
      for (int currentTagIndex = firstTagIndex; currentTagIndex <= lastTagIndex; currentTagIndex++) {
        PageElementTag currentTag = tags.get(currentTagIndex);
        if ((currentTagIndex == firstTagIndex) ||
            (currentTag.isFullTag()) ||
            (!currentTag.isEndTag())) {
          int testIndex = currentTag.getBeginIndex() - 1;
          while ((testIndex >= 0) && (Character.isWhitespace(contents.charAt(testIndex)))) {
            testIndex--;
          }
          if (testIndex >= 0) {
            char currentPunctuation = contents.charAt(testIndex);
View Full Code Here

Examples of org.wikipediacleaner.api.data.PageElementTag

58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
    String contents = analysis.getContents();
    for (PageElementInternalLink link : links) {
      // Check if it is an error
      boolean errorFound = Page.areSameTitle(pageTitle, link.getFullLink());
      if (errorFound) {
        PageElementTag tagIncludeOnly = analysis.getSurroundingTag(
            PageElementTag.TAG_WIKI_INCLUDEONLY, link.getBeginIndex());
        if (tagIncludeOnly != null) {
          errorFound = false;
        }
      }

      // Report error
      if (errorFound) {
        if (errors == null) {
          return true;
        }
        result = true;
        PageElementTag tagImagemap = analysis.getSurroundingTag(
            PageElementTag.TAG_WIKI_IMAGEMAP, link.getBeginIndex());
        if (tagImagemap != null) {
          int previousCR = getPreviousCR(contents, link.getBeginIndex());
          int nextCR = getNextCR(contents, link.getEndIndex());
          nextCR = Math.min(nextCR, tagImagemap.getMatchingTag().getBeginIndex());
          CheckErrorResult errorResult = createCheckErrorResult(
              analysis, previousCR, nextCR);
          if ((previousCR > tagImagemap.getEndIndex()) &&
              (contents.charAt(nextCR) == '\n')) {
            errorResult.addReplacement("", GT._("Delete"));
          }
          errors.add(errorResult);
        } else {
View Full Code Here

Examples of org.wikipediacleaner.api.data.PageElementTag

135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
    String pageTitle = analysis.getPage().getTitle();
    Collection<PageElementInternalLink> links = analysis.getInternalLinks();
    int currentIndex = 0;
    for (PageElementInternalLink link : links) {
      if (Page.areSameTitle(pageTitle, link.getFullLink())) {
        PageElementTag tagImagemap = analysis.getSurroundingTag(
            PageElementTag.TAG_WIKI_IMAGEMAP, link.getBeginIndex());
        if (tagImagemap != null) {
          int previousCR = getPreviousCR(contents, link.getBeginIndex());
          int nextCR = getNextCR(contents, link.getEndIndex());
          nextCR = Math.min(nextCR, tagImagemap.getMatchingTag().getBeginIndex());
          if ((previousCR > tagImagemap.getEndIndex()) &&
              (contents.charAt(nextCR) == '\n')) {
            if (previousCR > currentIndex) {
              newContents.append(contents.substring(currentIndex, previousCR));
              currentIndex = nextCR;
            }
View Full Code Here

Examples of org.wikipediacleaner.api.data.PageElementTag

65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
        if ((group != null) && (group.getValue() != null)) {
          groupName = group.getValue();
        }
 
        // Check if a <references> tag already exist for this group
        PageElementTag firstTag = firstTags.get(groupName);
        if (firstTag == null) {
          firstTags.put(groupName, referencesTag);
        } else {
          if (errors == null) {
            return true;
          }
          result = true;
          if (!tagUsed.contains(groupName)) {
            tagUsed.add(groupName);
            CheckErrorResult errorResult = createCheckErrorResult(
                analysis,
                firstTag.getCompleteBeginIndex(),
                firstTag.getCompleteEndIndex(),
                ErrorLevel.CORRECT);
            errorResult.addReplacement("");
            errors.add(errorResult);
          }
          CheckErrorResult errorResult = createCheckErrorResult(
View Full Code Here

Examples of org.wikipediacleaner.api.data.PageElementTag

55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
              int tmpIndex = paramValueStartIndex + currentPos;
              PageElementComment comment = analysis.isInComment(tmpIndex);
              if (comment != null) {
                currentPos = comment.getEndIndex() - 1 - paramValueStartIndex;
              } else {
                PageElementTag tag = analysis.isInTag(tmpIndex);
                if ((tag != null) &&
                    (tag.getBeginIndex() == tmpIndex) &&
                    ((PageElementTag.TAG_WIKI_MATH.equals(tag.getNormalizedName())) ||
                     (PageElementTag.TAG_WIKI_NOWIKI.equals(tag.getNormalizedName())) ||
                     (PageElementTag.TAG_WIKI_SOURCE.equals(tag.getNormalizedName())) ||
                     (PageElementTag.TAG_WIKI_SCORE.equals(tag.getNormalizedName())) ||
                     (PageElementTag.TAG_WIKI_SYNTAXHIGHLIGHT.equals(tag.getNormalizedName())))) {
                  currentPos = tag.getCompleteEndIndex() - 1 - paramValueStartIndex;
                }
              }
              break;
            case '[':
              squareBracketsCount++;
View Full Code Here

Examples of org.wikipediacleaner.api.data.PageElementTag

50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
    List<PageElementTag> refTags = analysis.getTags(PageElementTag.TAG_WIKI_REF);
    if ((refTags != null) && (refTags.size() > 0)) {
      Iterator<PageElementTag> itRefTags = refTags.iterator();
      while (!refFound && itRefTags.hasNext()) {
        boolean usefulRef = true;
        PageElementTag refTag = itRefTags.next();
        if (analysis.getSurroundingTag(PageElementTag.TAG_WIKI_NOWIKI, refTag.getBeginIndex()) != null) {
          usefulRef =  false;
        }
        if (usefulRef) {
          refFound = true;
        }
      }
    }
    if (!refFound) {
      return false;
    }

    // Analyzing text for <references> tags
    List<PageElementTag> referencesTags = analysis.getTags(PageElementTag.TAG_WIKI_REFERENCES);
    if (referencesTags != null) {
      for (PageElementTag referencesTag : referencesTags) {
        if (referencesTag.isComplete()) {
          return false;
        }
      }
    }

    // Search for templates like {{References}}
    String templates = getSpecificProperty(
        "templates", true, true, false);
    if (templates == null) {
      templates = getSpecificProperty(
          "references_templates", true, true, false);
    }
    List<String> referencesTemplates = null;
    if (templates != null) {
      referencesTemplates = WPCConfiguration.convertPropertyToStringList(templates);
    }
    if (referencesTemplates != null) {
      List<PageElementTemplate> allTemplates = analysis.getTemplates();
      int templateNum = allTemplates.size();
      while (templateNum > 0) {
        templateNum--;
        PageElementTemplate template = allTemplates.get(templateNum);
        for (String referencesTemplate : referencesTemplates) {
          if (Page.areSameTitle(template.getTemplateName(), referencesTemplate)) {
            return false;
          }
        }
      }
    }

    // Try to make some suggestions
    if (errors == null) {
      return true;
    }
    String contents = analysis.getContents();
    if (referencesTags != null) {
      for (PageElementTag referencesTag : referencesTags) {
        CheckErrorResult errorResult = createCheckErrorResult(
            analysis, referencesTag.getBeginIndex(), referencesTag.getEndIndex());
        if (referencesTags.size() == 1) {
          errorResult.addReplacement(
              PageElementTag.createTag(PageElementTag.TAG_WIKI_REFERENCES, true, true),
              GT._("Close tag"));
        }
        errors.add(errorResult);
        if (referencesTags.size() == 1) {
          int index = referencesTag.getEndIndex();
          boolean ok = true;
          while (ok && (index < contents.length())) {
            char currentChar = contents.charAt(index);
            if (Character.isWhitespace(currentChar)) {
              index++;
            } else if (currentChar == '<') {
              PageElementTag tag = analysis.isInTag(index);
              if ((tag != null) &&
                  (tag.getBeginIndex() == index) &&
                  (PageElementTag.TAG_WIKI_REF.equals(tag.getNormalizedName()))) {
                index = tag.getCompleteEndIndex();
              } else {
                if (contents.startsWith("</references/>", index)) {
                  errorResult = createCheckErrorResult(analysis, index, index + 14);
                  errorResult.addReplacement(PageElementTag.createTag(
                      PageElementTag.TAG_WIKI_REFERENCES, true, false), true);
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.