From a1383189225c6c3e180182d970a67aedc33be4aa Mon Sep 17 00:00:00 2001 From: Michael Block Date: Thu, 2 Jul 2020 10:26:33 +1200 Subject: [PATCH] ICU-21179 Clean up unused code in the RBBI dictbe The wordsMatched conditional gave the misleading impression that only the first "first word" candidate that was followed by a dictionary word would be marked, but because the wordsMatched declaration is inside the while loop, every "first word" candidate that's followed by a dictionary word is marked (resulting in the shortest and not the longest first candidate that's followed by a second dictionary word). --- icu4c/source/common/dictbe.cpp | 32 ++++++++------------------------ 1 file changed, 8 insertions(+), 24 deletions(-) diff --git a/icu4c/source/common/dictbe.cpp b/icu4c/source/common/dictbe.cpp index b42cdf03fae..44285755f3f 100644 --- a/icu4c/source/common/dictbe.cpp +++ b/icu4c/source/common/dictbe.cpp @@ -265,13 +265,9 @@ ThaiBreakEngine::divideUpDictionaryRange( UText *text, goto foundBest; } do { - int32_t wordsMatched = 1; if (words[(wordsFound + 1) % THAI_LOOKAHEAD].candidates(text, fDictionary, rangeEnd) > 0) { - if (wordsMatched < 2) { - // Followed by another dictionary word; mark first word as a good candidate - words[wordsFound%THAI_LOOKAHEAD].markCurrent(); - wordsMatched = 2; - } + // Followed by another dictionary word; mark first word as a good candidate + words[wordsFound%THAI_LOOKAHEAD].markCurrent(); // If we're already at the end of the range, we're done if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) { @@ -503,13 +499,9 @@ LaoBreakEngine::divideUpDictionaryRange( UText *text, goto foundBest; } do { - int32_t wordsMatched = 1; if (words[(wordsFound + 1) % LAO_LOOKAHEAD].candidates(text, fDictionary, rangeEnd) > 0) { - if (wordsMatched < 2) { - // Followed by another dictionary word; mark first word as a good candidate - words[wordsFound%LAO_LOOKAHEAD].markCurrent(); - wordsMatched = 2; - } + // Followed by another dictionary word; mark first word as a good candidate + words[wordsFound%LAO_LOOKAHEAD].markCurrent(); // If we're already at the end of the range, we're done if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) { @@ -699,13 +691,9 @@ BurmeseBreakEngine::divideUpDictionaryRange( UText *text, goto foundBest; } do { - int32_t wordsMatched = 1; if (words[(wordsFound + 1) % BURMESE_LOOKAHEAD].candidates(text, fDictionary, rangeEnd) > 0) { - if (wordsMatched < 2) { - // Followed by another dictionary word; mark first word as a good candidate - words[wordsFound%BURMESE_LOOKAHEAD].markCurrent(); - wordsMatched = 2; - } + // Followed by another dictionary word; mark first word as a good candidate + words[wordsFound%BURMESE_LOOKAHEAD].markCurrent(); // If we're already at the end of the range, we're done if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) { @@ -908,13 +896,9 @@ KhmerBreakEngine::divideUpDictionaryRange( UText *text, goto foundBest; } do { - int32_t wordsMatched = 1; if (words[(wordsFound + 1) % KHMER_LOOKAHEAD].candidates(text, fDictionary, rangeEnd) > 0) { - if (wordsMatched < 2) { - // Followed by another dictionary word; mark first word as a good candidate - words[wordsFound % KHMER_LOOKAHEAD].markCurrent(); - wordsMatched = 2; - } + // Followed by another dictionary word; mark first word as a good candidate + words[wordsFound % KHMER_LOOKAHEAD].markCurrent(); // If we're already at the end of the range, we're done if ((int32_t)utext_getNativeIndex(text) >= rangeEnd) {