001///////////////////////////////////////////////////////////////////////////////////////////////
002// checkstyle: Checks Java source code and other text files for adherence to a set of rules.
003// Copyright (C) 2001-2025 the original author or authors.
004//
005// This library is free software; you can redistribute it and/or
006// modify it under the terms of the GNU Lesser General Public
007// License as published by the Free Software Foundation; either
008// version 2.1 of the License, or (at your option) any later version.
009//
010// This library is distributed in the hope that it will be useful,
011// but WITHOUT ANY WARRANTY; without even the implied warranty of
012// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
013// Lesser General Public License for more details.
014//
015// You should have received a copy of the GNU Lesser General Public
016// License along with this library; if not, write to the Free Software
017// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
018///////////////////////////////////////////////////////////////////////////////////////////////
019
020package com.puppycrawl.tools.checkstyle.site;
021
022import java.lang.reflect.Field;
023import java.util.Optional;
024import java.util.Set;
025import java.util.regex.Pattern;
026
027import org.apache.maven.doxia.macro.MacroExecutionException;
028import org.apache.maven.doxia.sink.Sink;
029
030import com.puppycrawl.tools.checkstyle.PropertyType;
031import com.puppycrawl.tools.checkstyle.XdocsPropertyType;
032import com.puppycrawl.tools.checkstyle.api.DetailNode;
033import com.puppycrawl.tools.checkstyle.api.JavadocTokenTypes;
034import com.puppycrawl.tools.checkstyle.meta.JavadocMetadataScraperUtil;
035import com.puppycrawl.tools.checkstyle.utils.JavadocUtil;
036
037/**
038 * Utility class for parsing javadocs of modules.
039 */
040public final class ModuleJavadocParsingUtil {
041    /** New line escape character. */
042    public static final String NEWLINE = System.lineSeparator();
043    /** A newline with 8 spaces of indentation. */
044    public static final String INDENT_LEVEL_8 = SiteUtil.getNewlineAndIndentSpaces(8);
045    /** A newline with 10 spaces of indentation. */
046    public static final String INDENT_LEVEL_10 = SiteUtil.getNewlineAndIndentSpaces(10);
047    /** A newline with 12 spaces of indentation. */
048    public static final String INDENT_LEVEL_12 = SiteUtil.getNewlineAndIndentSpaces(12);
049    /** A newline with 14 spaces of indentation. */
050    public static final String INDENT_LEVEL_14 = SiteUtil.getNewlineAndIndentSpaces(14);
051    /** A newline with 16 spaces of indentation. */
052    public static final String INDENT_LEVEL_16 = SiteUtil.getNewlineAndIndentSpaces(16);
053    /** A newline with 18 spaces of indentation. */
054    public static final String INDENT_LEVEL_18 = SiteUtil.getNewlineAndIndentSpaces(18);
055    /** A newline with 20 spaces of indentation. */
056    public static final String INDENT_LEVEL_20 = SiteUtil.getNewlineAndIndentSpaces(20);
057    /** A set of all html tags that need to be considered as text formatting for this macro. */
058    public static final Set<String> HTML_TEXT_FORMAT_TAGS = Set.of("<code>", "<a", "</a>", "<b>",
059        "</b>", "<strong>", "</strong>", "<i>", "</i>", "<em>", "</em>", "<small>", "</small>",
060        "<ins>", "<sub>", "<sup>");
061    /** "Notes:" javadoc marking. */
062    public static final String NOTES = "Notes:";
063    /** "Notes:" line. */
064    public static final Pattern NOTES_LINE = Pattern.compile("\\s*" + NOTES + "$");
065    /** "Notes:" line with new line accounted. */
066    public static final Pattern NOTES_LINE_WITH_NEWLINE = Pattern.compile("\r?\n\\s?" + NOTES);
067
068    /**
069     * Private utility constructor.
070     */
071    private ModuleJavadocParsingUtil() {
072    }
073
074    /**
075     * Gets properties of the specified module.
076     *
077     * @param moduleName name of module.
078     * @return set of properties name if present, otherwise null.
079     * @throws MacroExecutionException if the module could not be retrieved.
080     */
081    public static Set<String> getPropertyNames(String moduleName)
082            throws MacroExecutionException {
083        final Object instance = SiteUtil.getModuleInstance(moduleName);
084        final Class<?> clss = instance.getClass();
085
086        return SiteUtil.getPropertiesForDocumentation(clss, instance);
087    }
088
089    /**
090     * Determines whether the given HTML node marks the start of the "Notes" section.
091     *
092     * @param htmlElement html element to check.
093     * @return true if the element starts the "Notes" section, false otherwise.
094     */
095    private static boolean isStartOfNotesSection(DetailNode htmlElement) {
096        final DetailNode paragraphNode = JavadocUtil.findFirstToken(
097            htmlElement, JavadocTokenTypes.PARAGRAPH);
098        final Optional<DetailNode> liNode = getLiTagNode(htmlElement);
099
100        return paragraphNode != null && JavadocMetadataScraperUtil.isChildNodeTextMatches(
101            paragraphNode, NOTES_LINE)
102            || liNode.isPresent() && JavadocMetadataScraperUtil.isChildNodeTextMatches(
103                liNode.get(), NOTES_LINE);
104    }
105
106    /**
107     * Gets the node of Li HTML tag.
108     *
109     * @param htmlElement html element to get li tag from.
110     * @return Optional of li tag node.
111     */
112    public static Optional<DetailNode> getLiTagNode(DetailNode htmlElement) {
113        return Optional.of(htmlElement)
114            .map(element -> JavadocUtil.findFirstToken(element, JavadocTokenTypes.HTML_TAG))
115            .map(element -> JavadocUtil.findFirstToken(element, JavadocTokenTypes.HTML_ELEMENT))
116            .map(element -> JavadocUtil.findFirstToken(element, JavadocTokenTypes.LI));
117    }
118
119    /**
120     * Writes the given javadoc chunk into xdoc.
121     *
122     * @param javadocPortion javadoc text.
123     * @param sink sink of the macro.
124     */
125    public static void writeOutJavadocPortion(String javadocPortion, Sink sink) {
126        final String[] javadocPortionLinesSplit = javadocPortion.split(NEWLINE
127            .replace("\r", ""));
128
129        sink.rawText(javadocPortionLinesSplit[0]);
130        String lastHtmlTag = javadocPortionLinesSplit[0];
131
132        for (int index = 1; index < javadocPortionLinesSplit.length; index++) {
133            final String currentLine = javadocPortionLinesSplit[index].trim();
134            final String processedLine;
135
136            if (currentLine.isEmpty()) {
137                processedLine = NEWLINE;
138            }
139            else if (currentLine.startsWith("<")
140                && !startsWithTextFormattingHtmlTag(currentLine)) {
141
142                processedLine = INDENT_LEVEL_8 + currentLine;
143                lastHtmlTag = currentLine;
144            }
145            else if (lastHtmlTag.contains("<pre")) {
146                final String currentLineWithPreservedIndent = javadocPortionLinesSplit[index]
147                    .substring(1);
148
149                processedLine = NEWLINE + currentLineWithPreservedIndent;
150            }
151            else {
152                processedLine = INDENT_LEVEL_10 + currentLine;
153            }
154
155            sink.rawText(processedLine);
156        }
157
158    }
159
160    /**
161     * Checks if given line starts with HTML text-formatting tag.
162     *
163     * @param line line to check on.
164     * @return whether given line starts with HTML text-formatting tag.
165     */
166    public static boolean startsWithTextFormattingHtmlTag(String line) {
167        boolean result = false;
168
169        for (String tag : HTML_TEXT_FORMAT_TAGS) {
170            if (line.startsWith(tag)) {
171                result = true;
172                break;
173            }
174        }
175
176        return result;
177    }
178
179    /**
180     * Gets the description of module from module javadoc.
181     *
182     * @param moduleJavadoc module javadoc.
183     * @return module description.
184     */
185    public static String getModuleDescription(DetailNode moduleJavadoc) {
186        final int descriptionEndIndex = getDescriptionEndIndex(moduleJavadoc);
187
188        return JavadocMetadataScraperUtil
189            .constructSubTreeText(moduleJavadoc, 0, descriptionEndIndex);
190    }
191
192    /**
193     * Gets the end index of the description.
194     *
195     * @param moduleJavadoc javadoc of module.
196     * @return the end index.
197     */
198    public static int getDescriptionEndIndex(DetailNode moduleJavadoc) {
199        int descriptionEndIndex = -1;
200
201        final int notesStartingIndex =
202            getNotesSectionStartIndex(moduleJavadoc);
203
204        if (notesStartingIndex > -1) {
205            descriptionEndIndex += notesStartingIndex;
206        }
207        else {
208            descriptionEndIndex += getModuleSinceVersionTagStartIndex(moduleJavadoc);
209        }
210
211        return descriptionEndIndex;
212    }
213
214    /**
215     * Gets the start index of the Notes section.
216     *
217     * @param moduleJavadoc javadoc of module.
218     * @return start index.
219     */
220    public static int getNotesSectionStartIndex(DetailNode moduleJavadoc) {
221        int notesStartIndex = -1;
222
223        for (DetailNode node : moduleJavadoc.getChildren()) {
224            if (node.getType() == JavadocTokenTypes.HTML_ELEMENT
225                && isStartOfNotesSection(node)) {
226
227                notesStartIndex += node.getIndex();
228                break;
229            }
230        }
231
232        return notesStartIndex;
233    }
234
235    /**
236     * Gets the starting index of the "@since" version tag in module's javadoc.
237     *
238     * @param moduleJavadoc javadoc of module.
239     * @return start index of "@since".
240     */
241    public static int getModuleSinceVersionTagStartIndex(DetailNode moduleJavadoc) {
242        return SiteUtil.getNodesOfSpecificType(moduleJavadoc.getChildren(),
243                JavadocTokenTypes.JAVADOC_TAG).stream()
244            .filter(javadocTag -> {
245                return JavadocUtil
246                    .findFirstToken(javadocTag, JavadocTokenTypes.SINCE_LITERAL) != null;
247            })
248            .findFirst()
249            .map(DetailNode::getIndex)
250            .orElse(-1);
251    }
252
253    /**
254     * Gets the Notes section of module from module javadoc.
255     *
256     * @param moduleJavadoc module javadoc.
257     * @return Notes section of module.
258     */
259    public static String getModuleNotes(DetailNode moduleJavadoc) {
260        final String result;
261
262        final int notesStartIndex = getNotesSectionStartIndex(moduleJavadoc);
263
264        if (notesStartIndex < 0) {
265            result = "";
266        }
267        else {
268            final int notesEndIndex = getNotesEndIndex(moduleJavadoc);
269
270            final String unprocessedNotes = JavadocMetadataScraperUtil.constructSubTreeText(
271                moduleJavadoc, notesStartIndex, notesEndIndex);
272
273            result = NOTES_LINE_WITH_NEWLINE.matcher(unprocessedNotes).replaceAll("");
274        }
275
276        return result;
277    }
278
279    /**
280     * Gets the end index of the Notes.
281     *
282     * @param moduleJavadoc javadoc of module.
283     * @return the end index.
284     */
285    public static int getNotesEndIndex(DetailNode moduleJavadoc) {
286        int notesEndIndex = -1;
287
288        notesEndIndex += getModuleSinceVersionTagStartIndex(moduleJavadoc);
289
290        return notesEndIndex;
291    }
292
293    /**
294     * Checks whether property is to contain tokens.
295     *
296     * @param propertyField property field.
297     * @return true if property is to contain tokens, false otherwise.
298     */
299    public static boolean isPropertySpecialTokenProp(Field propertyField) {
300        boolean result = false;
301
302        if (propertyField != null) {
303            final XdocsPropertyType fieldXdocAnnotation =
304                propertyField.getAnnotation(XdocsPropertyType.class);
305
306            result = fieldXdocAnnotation != null
307                && fieldXdocAnnotation.value() == PropertyType.TOKEN_ARRAY;
308        }
309
310        return result;
311    }
312
313}