| 1 | /******************************************************************************* | |
| 2 | * Copyright (C) 2026, Leo Galambos | |
| 3 | * All rights reserved. | |
| 4 | * | |
| 5 | * Redistribution and use in source and binary forms, with or without | |
| 6 | * modification, are permitted provided that the following conditions are met: | |
| 7 | * | |
| 8 | * 1. Redistributions of source code must retain the above copyright notice, | |
| 9 | * this list of conditions and the following disclaimer. | |
| 10 | * | |
| 11 | * 2. Redistributions in binary form must reproduce the above copyright notice, | |
| 12 | * this list of conditions and the following disclaimer in the documentation | |
| 13 | * and/or other materials provided with the distribution. | |
| 14 | * | |
| 15 | * 3. All advertising materials mentioning features or use of this software must | |
| 16 | * display the following acknowledgement: | |
| 17 | * This product includes software developed by the Egothor project. | |
| 18 | * | |
| 19 | * 4. Neither the name of the copyright holder nor the names of its contributors | |
| 20 | * may be used to endorse or promote products derived from this software | |
| 21 | * without specific prior written permission. | |
| 22 | * | |
| 23 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" | |
| 24 | * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE | |
| 25 | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE | |
| 26 | * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE | |
| 27 | * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR | |
| 28 | * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF | |
| 29 | * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS | |
| 30 | * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN | |
| 31 | * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) | |
| 32 | * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE | |
| 33 | * POSSIBILITY OF SUCH DAMAGE. | |
| 34 | ******************************************************************************/ | |
| 35 | package org.egothor.stemmer; | |
| 36 | ||
| 37 | import java.io.BufferedReader; | |
| 38 | import java.io.IOException; | |
| 39 | import java.io.Reader; | |
| 40 | import java.nio.charset.StandardCharsets; | |
| 41 | import java.nio.file.Files; | |
| 42 | import java.nio.file.Path; | |
| 43 | import java.util.Locale; | |
| 44 | import java.util.Objects; | |
| 45 | import java.util.StringTokenizer; | |
| 46 | import java.util.logging.Level; | |
| 47 | import java.util.logging.Logger; | |
| 48 | ||
| 49 | /** | |
| 50 | * Parser of line-oriented stemmer dictionary files. | |
| 51 | * | |
| 52 | * <p> | |
| 53 | * Each non-empty logical line consists of a stem followed by zero or more known | |
| 54 | * word variants separated by whitespace. The first token is interpreted as the | |
| 55 | * canonical stem, and every following token on the same line is interpreted as | |
| 56 | * a variant belonging to that stem. | |
| 57 | * | |
| 58 | * <p> | |
| 59 | * Input lines are normalized to lower case using {@link Locale#ROOT}. Leading | |
| 60 | * and trailing whitespace is ignored. | |
| 61 | * | |
| 62 | * <p> | |
| 63 | * The parser supports line remarks and trailing remarks. The remark markers | |
| 64 | * {@code #} and {@code //} terminate the logical content of the line, and the | |
| 65 | * remainder of that line is ignored. | |
| 66 | * | |
| 67 | * <p> | |
| 68 | * This class is intentionally stateless and allocation-light so it can be used | |
| 69 | * both by runtime loading and by offline compilation tooling. | |
| 70 | */ | |
| 71 | public final class StemmerDictionaryParser { | |
| 72 | ||
| 73 | /** | |
| 74 | * Logger of this class. | |
| 75 | */ | |
| 76 | private static final Logger LOGGER = Logger.getLogger(StemmerDictionaryParser.class.getName()); | |
| 77 | ||
| 78 | /** | |
| 79 | * Utility class. | |
| 80 | */ | |
| 81 | private StemmerDictionaryParser() { | |
| 82 | throw new AssertionError("No instances."); | |
| 83 | } | |
| 84 | ||
| 85 | /** | |
| 86 | * Callback receiving one parsed dictionary line. | |
| 87 | */ | |
| 88 | @FunctionalInterface | |
| 89 | public interface EntryHandler { | |
| 90 | ||
| 91 | /** | |
| 92 | * Accepts one parsed dictionary entry. | |
| 93 | * | |
| 94 | * @param stem canonical stem, never {@code null} | |
| 95 | * @param variants variants in encounter order, never {@code null} | |
| 96 | * @param lineNumber original physical line number in the parsed source | |
| 97 | * @throws IOException if processing fails | |
| 98 | */ | |
| 99 | void onEntry(String stem, String[] variants, int lineNumber) throws IOException; | |
| 100 | } | |
| 101 | ||
| 102 | /** | |
| 103 | * Parses a dictionary file from a filesystem path. | |
| 104 | * | |
| 105 | * @param path dictionary file path | |
| 106 | * @param entryHandler handler receiving parsed entries | |
| 107 | * @return parsing statistics | |
| 108 | * @throws NullPointerException if any argument is {@code null} | |
| 109 | * @throws IOException if reading fails | |
| 110 | */ | |
| 111 | public static ParseStatistics parse(final Path path, final EntryHandler entryHandler) throws IOException { | |
| 112 | Objects.requireNonNull(path, "path"); | |
| 113 | Objects.requireNonNull(entryHandler, "entryHandler"); | |
| 114 | ||
| 115 | try (BufferedReader reader = Files.newBufferedReader(path, StandardCharsets.UTF_8)) { | |
| 116 |
1
1. parse : replaced return value with null for org/egothor/stemmer/StemmerDictionaryParser::parse → KILLED |
return parse(reader, path.toAbsolutePath().toString(), entryHandler); |
| 117 | } | |
| 118 | } | |
| 119 | ||
| 120 | /** | |
| 121 | * Parses a dictionary file from a path string. | |
| 122 | * | |
| 123 | * @param fileName dictionary file name or path string | |
| 124 | * @param entryHandler handler receiving parsed entries | |
| 125 | * @return parsing statistics | |
| 126 | * @throws NullPointerException if any argument is {@code null} | |
| 127 | * @throws IOException if reading fails | |
| 128 | */ | |
| 129 | public static ParseStatistics parse(final String fileName, final EntryHandler entryHandler) throws IOException { | |
| 130 | Objects.requireNonNull(fileName, "fileName"); | |
| 131 |
1
1. parse : replaced return value with null for org/egothor/stemmer/StemmerDictionaryParser::parse → KILLED |
return parse(Path.of(fileName), entryHandler); |
| 132 | } | |
| 133 | ||
| 134 | /** | |
| 135 | * Parses a dictionary from a reader. | |
| 136 | * | |
| 137 | * @param reader source reader | |
| 138 | * @param sourceDescription logical source description for diagnostics | |
| 139 | * @param entryHandler handler receiving parsed entries | |
| 140 | * @return parsing statistics | |
| 141 | * @throws NullPointerException if any argument is {@code null} | |
| 142 | * @throws IOException if reading or handler processing fails | |
| 143 | */ | |
| 144 | public static ParseStatistics parse(final Reader reader, final String sourceDescription, | |
| 145 | final EntryHandler entryHandler) throws IOException { | |
| 146 | Objects.requireNonNull(reader, "reader"); | |
| 147 | Objects.requireNonNull(sourceDescription, "sourceDescription"); | |
| 148 | Objects.requireNonNull(entryHandler, "entryHandler"); | |
| 149 | ||
| 150 |
1
1. parse : negated conditional → KILLED |
final BufferedReader bufferedReader = reader instanceof BufferedReader ? (BufferedReader) reader |
| 151 | : new BufferedReader(reader); | |
| 152 | ||
| 153 | int lineNumber = 0; | |
| 154 | int logicalEntryCount = 0; | |
| 155 | int ignoredLineCount = 0; | |
| 156 | ||
| 157 |
1
1. parse : negated conditional → KILLED |
for (String line = bufferedReader.readLine(); line != null; line = bufferedReader.readLine()) { |
| 158 |
1
1. parse : Changed increment from 1 to -1 → KILLED |
lineNumber++; |
| 159 | ||
| 160 | final String normalizedLine = stripRemark(line).trim().toLowerCase(Locale.ROOT); | |
| 161 |
1
1. parse : negated conditional → KILLED |
if (normalizedLine.isEmpty()) { |
| 162 |
1
1. parse : Changed increment from 1 to -1 → KILLED |
ignoredLineCount++; |
| 163 | continue; | |
| 164 | } | |
| 165 | ||
| 166 | final StringTokenizer tokenizer = new StringTokenizer(normalizedLine); // NOPMD | |
| 167 |
1
1. parse : negated conditional → KILLED |
if (!tokenizer.hasMoreTokens()) { |
| 168 |
1
1. parse : Changed increment from 1 to -1 → NO_COVERAGE |
ignoredLineCount++; |
| 169 | continue; | |
| 170 | } | |
| 171 | ||
| 172 | final String stem = tokenizer.nextToken(); | |
| 173 | final String[] variants = new String[tokenizer.countTokens()]; // NOPMD | |
| 174 | ||
| 175 |
2
1. parse : changed conditional boundary → KILLED 2. parse : negated conditional → KILLED |
for (int index = 0; index < variants.length; index++) { |
| 176 | variants[index] = tokenizer.nextToken(); | |
| 177 | } | |
| 178 | ||
| 179 |
1
1. parse : removed call to org/egothor/stemmer/StemmerDictionaryParser$EntryHandler::onEntry → KILLED |
entryHandler.onEntry(stem, variants, lineNumber); |
| 180 |
1
1. parse : Changed increment from 1 to -1 → KILLED |
logicalEntryCount++; |
| 181 | } | |
| 182 | ||
| 183 | final ParseStatistics statistics = new ParseStatistics(sourceDescription, lineNumber, logicalEntryCount, | |
| 184 | ignoredLineCount); | |
| 185 | ||
| 186 | if (LOGGER.isLoggable(Level.FINE)) { | |
| 187 | LOGGER.log(Level.FINE, "Parsed dictionary source {0}: lines={1}, entries={2}, ignoredLines={3}.", | |
| 188 | new Object[] { statistics.sourceDescription(), statistics.lineCount(), statistics.entryCount(), | |
| 189 | statistics.ignoredLineCount() }); | |
| 190 | } | |
| 191 | ||
| 192 |
1
1. parse : replaced return value with null for org/egothor/stemmer/StemmerDictionaryParser::parse → KILLED |
return statistics; |
| 193 | } | |
| 194 | ||
| 195 | /** | |
| 196 | * Removes a trailing remark from one physical line. | |
| 197 | * | |
| 198 | * <p> | |
| 199 | * The earliest occurrence of either supported remark marker terminates the | |
| 200 | * logical line content. | |
| 201 | * | |
| 202 | * @param line physical line | |
| 203 | * @return line content without a trailing remark | |
| 204 | */ | |
| 205 | private static String stripRemark(final String line) { | |
| 206 | final int hashIndex = line.indexOf('#'); | |
| 207 | final int slashIndex = line.indexOf("//"); | |
| 208 | ||
| 209 | final int remarkIndex; | |
| 210 |
2
1. stripRemark : changed conditional boundary → KILLED 2. stripRemark : negated conditional → KILLED |
if (hashIndex < 0) { |
| 211 | remarkIndex = slashIndex; | |
| 212 |
2
1. stripRemark : changed conditional boundary → SURVIVED 2. stripRemark : negated conditional → KILLED |
} else if (slashIndex < 0) { |
| 213 | remarkIndex = hashIndex; | |
| 214 | } else { | |
| 215 | remarkIndex = Math.min(hashIndex, slashIndex); | |
| 216 | } | |
| 217 | ||
| 218 |
2
1. stripRemark : changed conditional boundary → KILLED 2. stripRemark : negated conditional → KILLED |
if (remarkIndex < 0) { |
| 219 |
1
1. stripRemark : replaced return value with "" for org/egothor/stemmer/StemmerDictionaryParser::stripRemark → KILLED |
return line; |
| 220 | } | |
| 221 |
1
1. stripRemark : replaced return value with "" for org/egothor/stemmer/StemmerDictionaryParser::stripRemark → KILLED |
return line.substring(0, remarkIndex); |
| 222 | } | |
| 223 | ||
| 224 | /** | |
| 225 | * Immutable parsing statistics. | |
| 226 | * | |
| 227 | * @param sourceDescription logical source description | |
| 228 | * @param lineCount number of physical lines read | |
| 229 | * @param entryCount number of logical dictionary entries emitted | |
| 230 | * @param ignoredLineCount number of ignored empty or remark-only lines | |
| 231 | */ | |
| 232 | public record ParseStatistics(String sourceDescription, int lineCount, int entryCount, int ignoredLineCount) { | |
| 233 | ||
| 234 | /** | |
| 235 | * Creates parsing statistics. | |
| 236 | * | |
| 237 | * @param sourceDescription logical source description | |
| 238 | * @param lineCount number of physical lines read | |
| 239 | * @param entryCount number of logical dictionary entries emitted | |
| 240 | * @param ignoredLineCount number of ignored empty or remark-only lines | |
| 241 | * @throws NullPointerException if {@code sourceDescription} is {@code null} | |
| 242 | * @throws IllegalArgumentException if any numeric value is negative | |
| 243 | */ | |
| 244 | public ParseStatistics { | |
| 245 | Objects.requireNonNull(sourceDescription, "sourceDescription"); | |
| 246 | if (lineCount < 0) { | |
| 247 | throw new IllegalArgumentException("lineCount must not be negative."); | |
| 248 | } | |
| 249 | if (entryCount < 0) { | |
| 250 | throw new IllegalArgumentException("entryCount must not be negative."); | |
| 251 | } | |
| 252 | if (ignoredLineCount < 0) { | |
| 253 | throw new IllegalArgumentException("ignoredLineCount must not be negative."); | |
| 254 | } | |
| 255 | } | |
| 256 | } | |
| 257 | } | |
Mutations | ||
| 116 |
1.1 |
|
| 131 |
1.1 |
|
| 150 |
1.1 |
|
| 157 |
1.1 |
|
| 158 |
1.1 |
|
| 161 |
1.1 |
|
| 162 |
1.1 |
|
| 167 |
1.1 |
|
| 168 |
1.1 |
|
| 175 |
1.1 2.2 |
|
| 179 |
1.1 |
|
| 180 |
1.1 |
|
| 192 |
1.1 |
|
| 210 |
1.1 2.2 |
|
| 212 |
1.1 2.2 |
|
| 218 |
1.1 2.2 |
|
| 219 |
1.1 |
|
| 221 |
1.1 |