Eliminate a redundant function call

5 files changed, 10 insertions, 15 deletions

diff --git a/stanza/utils/datasets/common.py b/stanza/utils/datasets/common.py
index a17db993..efdbb8cf 100644
--- a/stanza/utils/datasets/common.py
+++ b/stanza/utils/datasets/common.py
@@ -6,19 +6,10 @@ import os
 import sys
 
 import stanza.utils.default_paths as default_paths
-from stanza.models.common.constant import treebank_to_short_name
 from stanza.models.common.short_name_to_treebank import canonical_treebank_name
 
 logger = logging.getLogger('stanza')
 
-def project_to_short_name(treebank):
-    """
-    Project either a treebank or a short name to a short name
-
-    TODO: see if treebank_to_short_name can incorporate this
-    """
-    return treebank_to_short_name(treebank)
-
 def find_treebank_dataset_file(treebank, udbase_dir, dataset, extension, fail=False):
     """
     For a given treebank, dataset, extension, look for the exact filename to use.
diff --git a/stanza/utils/datasets/prepare_depparse_treebank.py b/stanza/utils/datasets/prepare_depparse_treebank.py
index 3152bfae..d452ac2c 100644
--- a/stanza/utils/datasets/prepare_depparse_treebank.py
+++ b/stanza/utils/datasets/prepare_depparse_treebank.py
@@ -14,6 +14,7 @@ import logging
 import os
 
 from stanza.models import tagger
+from stanza.models.common.constant import treebank_to_short_name
 from stanza.resources.common import download, DEFAULT_MODEL_DIR
 from stanza.resources.prepare_resources import default_charlms, pos_charlms
 import stanza.utils.datasets.common as common
@@ -67,7 +68,7 @@ def process_treebank(treebank, paths, args) -> None:
     if args.tag_method is Tags.GOLD:
         prepare_tokenizer_treebank.copy_conllu_treebank(treebank, paths, paths["DEPPARSE_DATA_DIR"])
     elif args.tag_method is Tags.PREDICTED:
-        short_name = common.project_to_short_name(treebank)
+        short_name = treebank_to_short_name(treebank)
         short_language, dataset = short_name.split("_")
 
         # fmt: off
diff --git a/stanza/utils/datasets/prepare_mwt_treebank.py b/stanza/utils/datasets/prepare_mwt_treebank.py
index 80881465..6d2c3e50 100644
--- a/stanza/utils/datasets/prepare_mwt_treebank.py
+++ b/stanza/utils/datasets/prepare_mwt_treebank.py
@@ -14,6 +14,7 @@ import os
 import shutil
 import tempfile
 
+from stanza.models.common.constant import treebank_to_short_name
 import stanza.utils.datasets.common as common
 import stanza.utils.datasets.prepare_tokenizer_treebank as prepare_tokenizer_treebank
 
@@ -25,7 +26,7 @@ def copy_conllu(tokenizer_dir, mwt_dir, short_name, dataset, particle):
     shutil.copyfile(input_conllu_tokenizer, input_conllu_mwt)
 
 def process_treebank(treebank, paths, args):
-    short_name = common.project_to_short_name(treebank)
+    short_name = treebank_to_short_name(treebank)
 
     mwt_dir = paths["MWT_DATA_DIR"]
     os.makedirs(mwt_dir, exist_ok=True)
diff --git a/stanza/utils/datasets/prepare_tokenizer_treebank.py b/stanza/utils/datasets/prepare_tokenizer_treebank.py
index d3b815f8..d03b81ac 100755
--- a/stanza/utils/datasets/prepare_tokenizer_treebank.py
+++ b/stanza/utils/datasets/prepare_tokenizer_treebank.py
@@ -31,6 +31,7 @@ import tempfile
 
 from collections import Counter
 
+from stanza.models.common.constant import treebank_to_short_name
 import stanza.utils.datasets.common as common
 import stanza.utils.datasets.prepare_tokenizer_data as prepare_tokenizer_data
 import stanza.utils.datasets.tokenization.convert_my_alt as convert_my_alt
@@ -56,7 +57,7 @@ def copy_conllu_treebank(treebank, paths, dest_dir, postprocess=None, augment=Tr
     """
     os.makedirs(dest_dir, exist_ok=True)
 
-    short_name = common.project_to_short_name(treebank)
+    short_name = treebank_to_short_name(treebank)
     short_language = short_name.split("_")[0]
 
     with tempfile.TemporaryDirectory() as tokenizer_dir:
@@ -1156,7 +1157,7 @@ def process_treebank(treebank, paths, args):
     tokenizer_dir = paths["TOKENIZE_DATA_DIR"]
     handparsed_dir = paths["HANDPARSED_DIR"]
 
-    short_name = common.project_to_short_name(treebank)
+    short_name = treebank_to_short_name(treebank)
     short_language = short_name.split("_")[0]
 
     os.makedirs(tokenizer_dir, exist_ok=True)
diff --git a/stanza/utils/training/run_ete.py b/stanza/utils/training/run_ete.py
index d4cc8a25..c4d146e3 100644
--- a/stanza/utils/training/run_ete.py
+++ b/stanza/utils/training/run_ete.py
@@ -28,9 +28,10 @@ from stanza.models import parser
 from stanza.models import tagger
 from stanza.models import tokenizer
 
+from stanza.models.common.constant import treebank_to_short_name
+
 from stanza.resources.prepare_resources import default_charlms, pos_charlms
 
-from stanza.utils.datasets.common import project_to_short_name
 from stanza.utils.training import common
 from stanza.utils.training.common import Mode, build_charlm_args, choose_charlm
 from stanza.utils.training.run_lemma import check_lemmas
@@ -65,7 +66,7 @@ def run_ete(paths, dataset, short_name, command_args, extra_args):
     # value of command_args.save_output
 
     if command_args and command_args.test_data:
-        test_short_name = project_to_short_name(command_args.test_data)
+        test_short_name = treebank_to_short_name(command_args.test_data)
     else:
         test_short_name = short_name