chore: import upstream snapshot with attribution

2026-07-13 13:24:13 +08:00
commit 1037506f2e
6050 changed files with 1731598 additions and 0 deletions
@@ -0,0 +1,52 @@
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--src', type=str, help='Source language')
+parser.add_argument('--tgt', type=str, help='Target language')
+parser.add_argument('--src-file', type=str, help='Input source file')
+parser.add_argument('--tgt-file', type=str, help='Input target file')
+parser.add_argument('--src-output-file', type=str, help='Output source file')
+parser.add_argument('--tgt-output-file', type=str, help='Output target file')
+parser.add_argument('--threshold', type=float, default=0.5, help='Threshold')
+parser.add_argument('--threshold-character', type=str, default=']', help='Threshold character')
+parser.add_argument('--histograms', type=str, help='Path to histograms')
+
+args = parser.parse_args()
+
+
+def read_hist(f):
+    ch = []
+    for line in f:
+        c = line[0]
+        if c == args.threshold_character:
+            break
+        ch.append(c)
+    return ch
+
+
+with(open("{}/{}".format(args.histograms, args.src), 'r', encoding='utf8')) as f:
+    ch1 = read_hist(f)
+
+with(open("{}/{}".format(args.histograms, args.tgt), 'r', encoding='utf8')) as f:
+    ch2 = read_hist(f)
+
+print("Accepted characters for {}: {}".format(args.src, ch1))
+print("Accepted characters for {}: {}".format(args.tgt, ch2))
+
+with open(args.src_file, 'r', encoding='utf8') as fs1, open(args.tgt_file, 'r', encoding='utf8') as fs2, open(args.src_output_file, 'w', encoding='utf8') as fos1, open(args.tgt_output_file, 'w', encoding='utf8') as fos2:
+    ls1 = fs1.readline()
+    ls2 = fs2.readline()
+
+    while ls1 or ls2:
+        cnt1 = len([c for c in ls1.strip() if c in ch1])
+        cnt2 = len([c for c in ls2.strip() if c in ch2])
+
+        if cnt1 / len(ls1) > args.threshold and cnt2 / len(ls2) > args.threshold:
+            fos1.write(ls1)
+            fos2.write(ls2)
+        else:
+            print("{} {} {} \n{} {} {}".format(args.src, cnt1 / len(ls1), ls1.strip(), args.tgt, cnt2 / len(ls2), ls2.strip()))
+
+        ls1 = fs1.readline()
+        ls2 = fs2.readline()
+        
@@ -0,0 +1,91 @@
+import argparse
+from collections import namedtuple
+import os
+
+DATADIR = "/path/to/train_data"
+DEDUP_FROM_DIR = "/path/to/eval/data"
+OUTPUT_DIR = "/path/to/output/data"
+
+
+def main(args):
+    languages = set()
+    for language_directory in os.listdir(DATADIR):
+        if "_" in language_directory:
+            src, tgt = language_directory.split("_")
+            languages.add(LanguagePair(src=src, tgt=tgt))
+
+    data = existing_data()
+    train_languages = sorted(languages)
+    for language_pair in train_languages[args.start_index:args.start_index + args.size]:
+        print(language_pair)
+        dedup(language_pair, data)
+
+
+LanguagePair = namedtuple("LanguagePair", ["src", "tgt"])
+
+
+def existing_data():
+    data = set()
+    for file in os.listdir(DEDUP_FROM_DIR):
+        with open(os.path.join(DEDUP_FROM_DIR, file)) as f:
+            data |= set(f.readlines())
+    return data
+ 
+def dedup(language_pair, data, verbose=True, output=True):
+    train_filenames = LanguagePair(
+            src=f"{DATADIR}/{language_pair.src}_{language_pair.tgt}/train.{language_pair.src}",
+            tgt=f"{DATADIR}/{language_pair.src}_{language_pair.tgt}/train.{language_pair.tgt}",
+        )
+
+    output_filenames = LanguagePair(
+        src=f"{OUTPUT_DIR}/train.dedup.{language_pair.src}-{language_pair.tgt}.{language_pair.src}",
+        tgt=f"{OUTPUT_DIR}/train.dedup.{language_pair.src}-{language_pair.tgt}.{language_pair.tgt}"
+    )
+
+    # If output exists, skip this pair. It has already been done.
+    if (os.path.exists(output_filenames.src) and
+        os.path.exists(output_filenames.tgt)):
+        if verbose:
+            print(f"{language_pair.src}-{language_pair.tgt} already done.")
+        return
+
+    if verbose:
+        print(f"{language_pair.src}-{language_pair.tgt} ready, will check dups.")
+
+    # If there is no output, no need to actually do the loop.
+    if not output:
+        return
+
+    if os.path.exists(train_filenames.src) and os.path.exists(train_filenames.tgt):
+        with open(train_filenames.src) as f:
+            train_source = f.readlines()
+
+        with open(train_filenames.tgt) as f:
+            train_target = f.readlines()
+
+        # do dedup
+        new_train_source = []
+        new_train_target = []
+        for i, train_line in enumerate(train_source):
+            if train_line not in data and train_target[i] not in data:
+                new_train_source.append(train_line)
+                new_train_target.append(train_target[i])
+
+        assert len(train_source) == len(train_target)
+        assert len(new_train_source) == len(new_train_target)
+        assert len(new_train_source) <= len(train_source)
+
+        with open(output_filenames.src, "w") as o:
+            for line in new_train_source:
+                o.write(line)
+
+        with open(output_filenames.tgt, "w") as o:
+            for line in new_train_target:
+                o.write(line)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-s", "--start-index", required=True, type=int)
+    parser.add_argument("-n", "--size", required=True, type=int)
+    main(parser.parse_args())
@@ -0,0 +1,36 @@
+import gzip
+import argparse
+from string import punctuation
+
+def len_no_punc(s, punc):
+    return len([ch for ch in s if ch in punc])
+
+def filter_overpunc(len_npunc, len_sen):
+    return len_npunc < 0.5*len_sen
+
+def main(args):
+    punc = punctuation + "—|–"
+    print('Processing file {}'.format(args.input))
+    with gzip.open(args.input, 'rt', encoding=args.encoding) as tsv:
+        with open(args.bitext + '.' + args.src_lang, 'wt', encoding=args.encoding) as fsrc:
+            with open(args.bitext + '.' + args.tgt_lang, 'wt', encoding=args.encoding) as ftgt:
+                line = tsv.readline()
+                fields = line.split('\t')
+
+                src, tgt = fields[1], fields[2]
+
+                nchar_npunc_src = len_no_punc(src, punc)
+                nchar_npunc_tgt = len_no_punc(tgt, punc)
+
+                if filter_overpunc(nchar_npunc_src, len(src)) and filter_overpunc(nchar_npunc_tgt, len(tgt)):
+                    fsrc.write(src.strip() + '\n')
+                    ftgt.write(tgt.strip() + '\n')
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--input", required=True, type=str)
+    parser.add_argument('--encoding', default='utf-8', help='character encoding for input/output')
+    parser.add_argument('--bitext', type=str, required=True, help='language direction')
+    parser.add_argument('--src-lang', type=str, required=True, help='Source language')
+    parser.add_argument('--tgt-lang', type=str, required=True, help='Target language')
+    main(parser.parse_args())