Add first tests
Change-Id: I7ef95cef912feb2b997e1c7da5eb5a369cbe56b1
diff --git a/tests/basic_test.c b/tests/basic_test.c
new file mode 100644
index 0000000..d58dbe6
--- /dev/null
+++ b/tests/basic_test.c
@@ -0,0 +1,129 @@
+#include <stdio.h>
+#include <string.h>
+#define __USE_XOPEN_EXTENDED
+#include <ftw.h>
+#include "../src/collocatordb.h"
+#include "acutest.h"
+
+char dbpath[] = "../tests/data/wpd19_10000";
+const int testword = 10; // ist
+
+void test_open_db() {
+ COLLOCATORDB *cdb;
+
+ cdb = open_collocatordb(dbpath);
+ TEST_ASSERT(cdb != NULL);
+}
+
+void test_get_word() {
+ COLLOCATORDB *cdb;
+
+ cdb = open_collocatordb(dbpath);
+ TEST_ASSERT(cdb != NULL);
+ char *word = get_word(cdb, testword);
+ char *expected = "ist";
+ TEST_CHECK(strcmp(word, expected) == 0);
+ TEST_MSG("Expected: %s", expected);
+ TEST_MSG("Produced: %s", word);
+}
+
+void test_collocation_scores() {
+ COLLOCATORDB *cdb;
+
+ cdb = open_collocatordb(dbpath);
+ TEST_ASSERT(cdb != NULL);
+ char *expected = " { \"f1\": 217,\"w1\":\"Aluminium\", \"N\": 152744, \"collocates\": [{\"word\":\"Anwendungstechnologie\",\"f2\":16,\"f\":16,\"npmi\":0.594849,\"pmi\":8.4592,\"llr\":188.227,\"lfmd\":16.4592,\"md\":12.4592,\"dice\":0.0711111,\"ld\":10.1862,\"ln_count\":16,\"rn_count\":0,\"ln_pmi\":9.4592,\"rn_pmi\":-1,\"ldaf\":11.1358,\"win\":32,\"afwin\":32}]}\n";
+ char *produced = get_collocation_scores_as_json(cdb, 62, 966);
+ TEST_CHECK(strcmp(produced, expected) == 0);
+ TEST_MSG("Expected: %s", expected);
+ TEST_MSG("Produced: %s", produced);
+}
+
+
+void test_collocation_analysis_as_json() {
+ COLLOCATORDB *cdb;
+
+ cdb = open_collocatordb(dbpath);
+ TEST_ASSERT(cdb != NULL);
+ char *json = get_collocators_as_json(cdb, testword);
+ char *needle = "\"word\":\"um\",\"f2\":264,\"f\":5,\"npmi\":-0.0556343,\"pmi\":-0.958064,\"llr\":2.87717,\"lfmd\":3.68579,\"md\":1.36386,\"dice\":0.00169952,\"ld\":4.79935,\"ln_count\":0,\"rn_count\":1,\"ln_pmi\":-1,\"rn_pmi\":-1,\"ldaf\":4.79935,\"win\":668,\"afwin\":668";
+ TEST_CHECK(strstr(json, needle) > 0);
+ TEST_MSG("Expected to contain: %s", needle);
+ const COLLOCATOR *c = get_collocators(cdb, 62);
+ printf("%s %lu\n", get_word(cdb,c[0].w2), c[0].f2);
+}
+
+void test_collocation_analysis() {
+ COLLOCATORDB *cdb;
+
+ cdb = open_collocatordb(dbpath);
+ TEST_ASSERT(cdb != NULL);
+ char *expected = "Anwendungstechnologie";
+ const COLLOCATOR *c = get_collocators(cdb, 62);
+ char *produced = get_word(cdb,c[0].w2);
+ TEST_CHECK(strcmp(produced, expected) == 0);
+ TEST_MSG("Expected: %s", expected);
+ TEST_MSG("Produced: %s", produced);
+ printf("%s\n", get_collocators_as_json(cdb,62));
+
+}
+
+int unlink_cb(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftwbuf) {
+ int rv = remove(fpath);
+ if (rv)
+ perror(fpath);
+ return rv;
+}
+
+int rmrf(char *path) {
+ return nftw(path, unlink_cb, 64, FTW_DEPTH | FTW_PHYS);
+}
+
+void test_writing() {
+ char *tmp = tempnam(NULL, NULL);
+ long size = 0;
+
+ printf("%s\n", acutest_argv0_);
+
+ char *rocksdbfn = malloc(strlen(tmp)+strlen(".rocksdb"));
+ strcpy (rocksdbfn, tmp);
+ strcat(rocksdbfn, ".rocksdb");
+ COLLOCATORDB *cdb = open_collocatordb_for_write(rocksdbfn);
+
+ char *vocabfn = malloc(strlen(tmp)+strlen(".vocab"));
+ strcpy(vocabfn, tmp);
+ strcat(vocabfn, ".vocab");
+ FILE *h = fopen(vocabfn, "w");
+ fprintf(h, "word0 2000\n");
+ fprintf(h, "word1 2000\n");
+ fprintf(h, "word2 2000\n");
+ fclose(h);
+ read_vocab(cdb, vocabfn);
+ inc_collocator(cdb, 0, 1, 4); size++;
+ for (int i=0; i < 1000; i++) {
+ inc_collocator(cdb, 0, 1, i % 5); size++;
+ inc_collocator(cdb, 0, 1, -i % 5); size++;
+ inc_collocator(cdb, 1, 0, i % 5); size++;
+ inc_collocator(cdb, 1, 0, -i % 5); size++;
+ inc_collocator(cdb, 0, 2, i % 5); size++;
+ inc_collocator(cdb, 0, 2, -i % 5); size++;
+ }
+ inc_collocator(cdb, 1, 2, 4); size++;
+ COLLOCATOR *c = get_collocators(cdb, 0);
+ TEST_ASSERT(c != NULL);
+ TEST_CHECK(c[0].raw == 2001);
+ TEST_CHECK(c[0].left_raw == 200);
+ TEST_CHECK(c[0].right_raw == 200);
+
+ rmrf(rocksdbfn);
+}
+
+TEST_LIST = {
+ { "open database for reading", test_open_db },
+ { "get word", test_get_word },
+ { "collocation scores", test_collocation_scores },
+ { "collocation analysis", test_collocation_analysis },
+ { "collocation analysis as json", test_collocation_analysis_as_json },
+ { "writing", test_writing },
+ { NULL, NULL }
+};