mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2025-01-19 06:53:36 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity

Update file paths in dawg_test

Browse Source 
Get unicharset and wordlist files from test/testing and use the latest
test submodule which provides those files.

Signed-off-by: Stefan Weil <sw@weilnetz.de>
This commit is contained in:
Stefan Weil 2019-01-21 18:00:08 +01:00
parent 57f74d2b73
commit 2c0ddb4220
2 changed files with 4 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
test

@ -1 +1 @@
Subproject commit c1d4c0d91c3d290841ab2e77a562cce0e1225731
Subproject commit 872b8963ecf00a4cd26a9fa2caefc1cd7e03da53

9
unittest/dawg_test.cc
View File

@ -42,9 +42,6 @@ class DawgTest : public testing::Test {
file.close();
}
}
std::string TestDataNameToPath(const std::string& name) const {
return file::JoinPath(TESTDATA_DIR, name);
}
std::string TessBinaryPath(const std::string& name) const {
return file::JoinPath(TESSBIN_DIR, "src/training/" + name);
}
@ -63,8 +60,8 @@ class DawgTest : public testing::Test {
void TestDawgRoundTrip(const std::string& unicharset_filename,
const std::string& wordlist_filename) const {
std::set<std::string> orig_words, roundtrip_words;
std::string unicharset = TestDataNameToPath(unicharset_filename);
std::string orig_wordlist = TestDataNameToPath(wordlist_filename);
std::string unicharset = file::JoinPath(TESTING_DIR, unicharset_filename);
std::string orig_wordlist = file::JoinPath(TESTING_DIR, wordlist_filename);
std::string output_dawg = OutputNameToPath(wordlist_filename + ".dawg");
std::string output_wordlist = OutputNameToPath(wordlist_filename);
LoadWordlist(orig_wordlist, &orig_words);
@ -84,7 +81,7 @@ TEST_F(DawgTest, TestDawgConversion) {
TEST_F(DawgTest, TestMatching) {
UNICHARSET unicharset;
unicharset.load_from_file(TestDataNameToPath("eng.unicharset").c_str());
unicharset.load_from_file(file::JoinPath(TESTING_DIR, "eng.unicharset").c_str());
tesseract::Trie trie(tesseract::DAWG_TYPE_WORD, "basic_dawg", NGRAM_PERM,
unicharset.size(), 0);
WERD_CHOICE space_apos(" '", unicharset);