solved bible

app/crud/nlp_crud.py

@@ -84,7 +84,7 @@ def get_project_tokens(db_:Session, project_id, books, sentence_id_range, senten
         raise NotAvailableException(f"Project with id, {project_id}, not found")
     sentences = projects_crud.obtain_project_source(db_, project_id, books, sentence_id_range,
         sentence_id_list)
-    sentences = sentences['db_content']
+    # sentences = sentences['db_content']
     args = {"db_":db_, "src_language":project_row.sourceLanguage, "sentence_list":sentences,
         'trg_language':project_row.targetLanguage,
         "use_translation_memory":use_translation_memory, "include_phrases":include_phrases,
@@ -93,12 +93,12 @@ def get_project_tokens(db_:Session, project_id, books, sentence_id_range, senten
         args['stopwords'] = project_row.metaData['stopwords']
     if "punctuations" in project_row.metaData:
         args['punctuations'] = project_row.metaData['punctuations']
-    # return get_generic_tokens( **args)
-    response = {
-        'db_content':get_generic_tokens( **args),
-        'project_content':project_row
-        }
-    return response
+    return get_generic_tokens( **args)
+    # response = {
+    #     'db_content':get_generic_tokens( **args),
+    #     'project_content':project_row
+    #     }
+    # return response
 
 ###################### Token replacement translation ######################
 def replace_bulk_tokens_gloss_list(token_translations, updated_sentences):
@@ -895,6 +895,7 @@ def obtain_draft(sentence_list, doc_type):
         return result
     return None
 
+
 def create_usfm(sent_drafts):
     '''Creates minimal USFM file with basic markers from the input verses list
     input: List of (bbbcccvvv, "generated translation")
@@ -931,6 +932,7 @@ def create_usfm(sent_drafts):
         usfm_files.append(file)
     return usfm_files
 
+
 def export_to_print(sentence_list):
     '''get a response with just id and draft to print'''
     output_json = {}

app/crud/projects_crud.py

@@ -101,6 +101,7 @@ def get_sentences_from_usfm_json(contents_list, book_code, book_id):
     surrogate_id = book_code
     found_split_verse = None
     splits = []
+    print("contents_list",contents_list)
     for node in contents_list:
         if isinstance(node, str):
             sent_id = book_id*1000000+int(curr_chap)*1000+verse_number_int
@@ -150,7 +151,8 @@ def get_sentences_from_usfm_json(contents_list, book_code, book_id):
 def update_translation_project_uploaded_book(db_,project_obj,project_id,new_books,user_id):
     """bulk uploaded book update in update translation project"""
     for usfm in project_obj.uploadedUSFMs:
-        usfm_parser = USFMParser(usfm)
+        # usfm_parser = USFMParser(usfm)
+        usfm_parser = USFMParser(utils.normalize_unicode(usfm))
         # usfm_json = utils.parse_usfm(usfm)
         usfm_json =usfm_parser.to_usj(include_markers=Filter.BCV+Filter.TEXT)
         book_code = usfm_json['content'][0]['code'].lower()
@@ -159,6 +161,8 @@ def update_translation_project_uploaded_book(db_,project_obj,project_id,new_book
         book_id = utils.BOOK_CODES[book_code.lower()]['book_num']
         new_books.append(book_code)
         draft_rows = get_sentences_from_usfm_json(usfm_json['content'], book_code, book_id)
+        print("draft_rows",draft_rows)
+        print("usfm_json['content']",usfm_json['content'])
         for item in draft_rows:
             db_.add(db_models.TranslationDraft(
                 project_id=project_id,
@@ -409,9 +413,9 @@ def obtain_project_draft(db_:Session, project_id, books, sentence_id_list, sente
     draft_rows = draft_rows['db_content']
     if output_format == schemas_nlp.DraftFormats.USFM :
         draft_out = nlp_crud.create_usfm(draft_rows)
-    # elif output_format == schemas_nlp.DraftFormats.JSON:
-    #     draft_out = nlp_crud.export_to_json(project_row.sourceLanguage,
-    #         project_row.targetLanguage, draft_rows, None)
+    elif output_format == schemas_nlp.DraftFormats.JSON:
+        draft_out = nlp_crud.export_to_json(project_row.sourceLanguage,
+            project_row.targetLanguage, draft_rows, None)
     elif output_format == schemas_nlp.DraftFormats.PRINT:
         draft_out = nlp_crud.export_to_print(draft_rows)
     else:
@@ -764,11 +768,12 @@ def obtain_project_source(db_:Session, project_id, books=None, sentence_id_range
                 "surrogateId":row.surrogateId,"sentence":row.sentence}
             result.append(obj)
 
-    response = {
-        'db_content':result,
-        'project_content':project_row
-        }
-    return response
+    # response = {
+    #     'db_content':result,
+    #     'project_content':project_row
+    #     }
+    # return response
+    return result
 
 def remove_project_sentence(db_, project_id, sentence_id,user_id):
     '''To remove a sentence'''
@@ -785,7 +790,7 @@ def remove_project_sentence(db_, project_id, sentence_id,user_id):
     db_.delete(sentence_row)
     project_row.updatedUser = user_id
     project_row.updateTime = datetime.datetime.now(ist_timezone).strftime('%Y-%m-%d %H:%M:%S')
-    # db_.commit()
+    db_.commit()
     response = {
         "db_content": sentence_row,
         "project_content": project_row

app/test/test_agmt_projects.py

@@ -1328,7 +1328,7 @@ def test_bugfix_split_n_merged_verse():
     }
     headers_auth['Authorization'] = "Bearer"+" "+initial_test_users['AgAdmin']['token']
     response = client.post(UNIT_URL, headers=headers_auth, json=post_data)
-    print("RESPONSE1",response.json())
+    # print("RESPONSE1",response.json())
     assert response.status_code == 201
     assert response.json()['message'] == "Project created successfully"
     project_id = response.json()['data']['projectId']
@@ -1341,12 +1341,19 @@ def test_bugfix_split_n_merged_verse():
     }
     prj_update_resp = client.put(UNIT_URL+'?project_id='+str(project_id),\
          json=prj_book_data, headers=headers_auth)
-    print("RESPONSE2",prj_update_resp.json())
+    # print("RESPONSE2",prj_update_resp.json())
     assert prj_update_resp.status_code == 201
     resp_obj = prj_update_resp.json()
     # print("RESPONSE3",resp_obj)
     assert resp_obj['message'] == 'Project updated successfully'
-
+    # print("USFM Data:", prj_book_data)
+    # # print("Project Update Response:", resp_obj)
+    # for verse_content in prj_book_data["uploadedUSFMs"]:
+    #     verses = verse_content.split('\n\\v ')
+    #     for verse in verses[1:]:  # Skip the first element as it contains metadata
+    #         print("Processing Verse:", '\\v ' + verse)
+    #         verse_parts = verse.split(' ')  # Split by space to get individual components
+    #         print("Verse Parts:", verse_parts)
     sentences_resp = client.get(f"{SENTENCE_URL}?project_id={project_id}", headers=headers_auth)
     assert sentences_resp.status_code == 200
     sentences = sentences_resp.json()