Merge pull request bfsujason#3 from ProMeText/update_imports

Update imports
matgille · Apr 19, 2024 · 5e90057 · 5e90057
2 parents 6a637d8 + 42a8ab3
commit 5e90057
Show file tree

Hide file tree

Showing 29 changed files with 5,352 additions and 12 deletions.
diff --git a/Bertalign.egg-info/PKG-INFO b/Bertalign.egg-info/PKG-INFO
@@ -0,0 +1,11 @@
+Metadata-Version: 2.1
+Name: Bertalign
+Version: 0.1.0
+Summary: An automatic mulitlingual sentence aligner.
+Home-page: https://github.com/bfsujason/bertalign
+License: UNKNOWN
+Platform: UNKNOWN
+License-File: LICENCE
+
+UNKNOWN
+
diff --git a/Bertalign.egg-info/SOURCES.txt b/Bertalign.egg-info/SOURCES.txt
@@ -0,0 +1,7 @@
+LICENCE
+README.md
+setup.py
+Bertalign.egg-info/PKG-INFO
+Bertalign.egg-info/SOURCES.txt
+Bertalign.egg-info/dependency_links.txt
+Bertalign.egg-info/top_level.txt
diff --git a/Bertalign.egg-info/dependency_links.txt b/Bertalign.egg-info/dependency_links.txt
@@ -0,0 +1 @@
+
diff --git a/Bertalign.egg-info/top_level.txt b/Bertalign.egg-info/top_level.txt
@@ -0,0 +1 @@
+
diff --git a/aquilign/align/bertalign/Bertalign.py b/aquilign/align/bertalign/Bertalign.py
@@ -5,7 +5,7 @@
 __author__ = "Jason ([email protected])"
 __version__ = "1.1.0"
 
-from bertalign.encoder import Encoder
+from aquilign.align.bertalign.encoder import Encoder
 # from sonar.inference_pipelines.text import TextToEmbeddingModelPipeline
 # See other cross-lingual embedding models at
 # https://www.sbert.net/docs/pretrained_models.html
@@ -19,4 +19,4 @@
 # nb = input(f'Choose a model:')
 model = Encoder(models[int(1)])
 
-from bertalign.aligner import Bertalign
+from aquilign.align.bertalign.aligner import Bertalign
diff --git a/aquilign/align/bertalign/aligner.py b/aquilign/align/bertalign/aligner.py
@@ -1,8 +1,8 @@
 import numpy as np
 
-from bertalign.Bertalign import model
-import bertalign.corelib as core
-import bertalign.utils as utils
+from aquilign.align.bertalign.Bertalign import model
+import aquilign.align.bertalign.corelib as core
+import aquilign.align.bertalign.utils as utils
 import torch.nn as nn
 import torch
 

diff --git a/aquilign/align/bertalign/encoder.py b/aquilign/align/bertalign/encoder.py
@@ -1,7 +1,7 @@
 import numpy as np
 import torch
 from sentence_transformers import SentenceTransformer
-from bertalign.utils import yield_overlaps
+from aquilign.align.bertalign.utils import yield_overlaps
 # from sonar.inference_pipelines.text import TextToEmbeddingModelPipeline
 
 

diff --git a/aquilign/align/bertalign/syntactic_tokenization.py b/aquilign/align/bertalign/syntactic_tokenization.py
@@ -5,7 +5,7 @@
 import json
 import sys
 import langid 
-import bertalign.utils as utils
+import aquilign.align.bertalign.utils as utils
 
 def syntactic_tokenization(path, corpus_limit=None, use_punctuation=True):
     name = path.split("/")[-1].split(".")[0]
@@ -16,7 +16,7 @@ def syntactic_tokenization(path, corpus_limit=None, use_punctuation=True):
     codelang, _ = langid.classify(text[:300])
     print(text)
     print(codelang)
-    with open("bertalign/delimiters.json", "r") as input_json:
+    with open("aquilign/align/bertalign/delimiters.json", "r") as input_json:
         dictionary = json.load(input_json)
     # Il ne reconnaît pas toujours le castillan
     if codelang == "an":

diff --git a/data/extraitsLancelot/fr111-ii-48.txt → data/extraitsLancelot/ii-48/fr111-ii-48.txt b/data/extraitsLancelot/fr111-ii-48.txt → data/extraitsLancelot/ii-48/fr111-ii-48.txt
diff --git a/data/extraitsLancelot/fr751-ii-48.txt → data/extraitsLancelot/ii-48/fr751-ii-48.txt b/data/extraitsLancelot/fr751-ii-48.txt → data/extraitsLancelot/ii-48/fr751-ii-48.txt
diff --git a/data/extraitsLancelot/inc-ii-48.txt → data/extraitsLancelot/ii-48/inc-ii-48.txt b/data/extraitsLancelot/inc-ii-48.txt → data/extraitsLancelot/ii-48/inc-ii-48.txt
diff --git a/data/extraitsLancelot/lancellotto-ii-48.txt → ...raitsLancelot/ii-48/lancellotto-ii-48.txt b/data/extraitsLancelot/lancellotto-ii-48.txt → ...raitsLancelot/ii-48/lancellotto-ii-48.txt
diff --git a/data/extraitsLancelot/lanzarote-ii-48.txt → ...xtraitsLancelot/ii-48/lanzarote-ii-48.txt b/data/extraitsLancelot/lanzarote-ii-48.txt → ...xtraitsLancelot/ii-48/lanzarote-ii-48.txt
diff --git a/data/extraitsLancelot/micha_ii-48.txt → data/extraitsLancelot/ii-48/micha_ii-48.txt b/data/extraitsLancelot/micha_ii-48.txt → data/extraitsLancelot/ii-48/micha_ii-48.txt
diff --git a/.../extraitsLancelot/sommer_tome_4-ii-48.txt → ...itsLancelot/ii-48/sommer_tome_4-ii-48.txt b/.../extraitsLancelot/sommer_tome_4-ii-48.txt → ...itsLancelot/ii-48/sommer_tome_4-ii-48.txt
diff --git a/data/extraitsLancelot/ii-61/fr111-ii-61.txt b/data/extraitsLancelot/ii-61/fr111-ii-61.txt
diff --git a/data/extraitsLancelot/ii-61/fr751-ii-61.txt b/data/extraitsLancelot/ii-61/fr751-ii-61.txt
diff --git a/data/extraitsLancelot/inc-ii-61.txt → data/extraitsLancelot/ii-61/inc-ii-61.txt b/data/extraitsLancelot/inc-ii-61.txt → data/extraitsLancelot/ii-61/inc-ii-61.txt
diff --git a/data/extraitsLancelot/lancellotto-ii-61.txt → ...raitsLancelot/ii-61/lancellotto-ii-61.txt b/data/extraitsLancelot/lancellotto-ii-61.txt → ...raitsLancelot/ii-61/lancellotto-ii-61.txt
diff --git a/data/extraitsLancelot/lanzarote-ii-61.txt → ...xtraitsLancelot/ii-61/lanzarote-ii-61.txt b/data/extraitsLancelot/lanzarote-ii-61.txt → ...xtraitsLancelot/ii-61/lanzarote-ii-61.txt
diff --git a/data/extraitsLancelot/micha_ii-61.txt → data/extraitsLancelot/ii-61/micha_ii-61.txt b/data/extraitsLancelot/micha_ii-61.txt → data/extraitsLancelot/ii-61/micha_ii-61.txt
diff --git a/.../extraitsLancelot/sommer_tome_4-ii-61.txt → ...itsLancelot/ii-61/sommer_tome_4-ii-61.txt b/.../extraitsLancelot/sommer_tome_4-ii-61.txt → ...itsLancelot/ii-61/sommer_tome_4-ii-61.txt
diff --git a/data/extraitsLancelot/iv-75/fr111-iv-75.txt b/data/extraitsLancelot/iv-75/fr111-iv-75.txt
diff --git a/data/extraitsLancelot/inc-iv-75.txt → data/extraitsLancelot/iv-75/inc-iv-75.txt b/data/extraitsLancelot/inc-iv-75.txt → data/extraitsLancelot/iv-75/inc-iv-75.txt
diff --git a/data/extraitsLancelot/lancellotto-iv-75.txt → ...raitsLancelot/iv-75/lancellotto-iv-75.txt b/data/extraitsLancelot/lancellotto-iv-75.txt → ...raitsLancelot/iv-75/lancellotto-iv-75.txt
diff --git a/data/extraitsLancelot/lanzarote-iv-75.txt → ...xtraitsLancelot/iv-75/lanzarote-iv-75.txt b/data/extraitsLancelot/lanzarote-iv-75.txt → ...xtraitsLancelot/iv-75/lanzarote-iv-75.txt
diff --git a/data/extraitsLancelot/micha_iv-75.txt → data/extraitsLancelot/iv-75/micha_iv-75.txt b/data/extraitsLancelot/micha_iv-75.txt → data/extraitsLancelot/iv-75/micha_iv-75.txt
diff --git a/.../extraitsLancelot/sommer_tome_5_iv-75.txt → ...itsLancelot/iv-75/sommer_tome_5_iv-75.txt b/.../extraitsLancelot/sommer_tome_5_iv-75.txt → ...itsLancelot/iv-75/sommer_tome_5_iv-75.txt
diff --git a/main.py b/main.py
@@ -6,10 +6,10 @@
 import sys
 import numpy as np
 # import collatex
-import graph_merge
-import bertalign.utils as utils
-import bertalign.syntactic_tokenization as syntactic_tokenization
-from bertalign.Bertalign import Bertalign
+import aquilign.align.graph_merge as graph_merge
+import aquilign.align.bertalign.utils as utils
+import aquilign.align.bertalign.syntactic_tokenization as syntactic_tokenization
+from aquilign.align.bertalign.Bertalign import Bertalign
 import pandas as pd
 import argparse
 import glob
@@ -81,6 +81,10 @@ def __init__(self, corpus_size:None,
         self.use_punctiation = use_punctuation
         self.prefix = prefix
 
+        try:
+            os.mkdir(f"result_dir")
+        except FileExistsError:
+            pass
         try:
             os.mkdir(f"result_dir/{self.out_dir}/")
         except FileExistsError: