airbyte-source-google-sheets 0.10.0.dev202505231635__py3-none-any.whl → 0.10.0.dev202506022219__py3-none-any.whl

{airbyte_source_google_sheets-0.10.0.dev202505231635.dist-info → airbyte_source_google_sheets-0.10.0.dev202506022219.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: airbyte-source-google-sheets
-Version: 0.10.0.dev202505231635
+Version: 0.10.0.dev202506022219
 Summary: Source implementation for Google Sheets.
 License: Elv2
 Author: Airbyte

{airbyte_source_google_sheets-0.10.0.dev202505231635.dist-info → airbyte_source_google_sheets-0.10.0.dev202506022219.dist-info}/RECORD

@@ -2,15 +2,15 @@ source_google_sheets/__init__.py,sha256=dYaZS0KrTjksk_yeSuXmNDXDsNKWctFnlZJSMgLr
 source_google_sheets/components/__init__.py,sha256=v7odPaLdz2S_NRzExsxkk6694Vmjbplz4Z5mA4lxdkA,343
 source_google_sheets/components/extractors.py,sha256=-d5hPW40ZBjU3gTUZNudayvqf1eHlveW1amwKJywDkU,9668
 source_google_sheets/components/partition_routers.py,sha256=SWo1V0K10ZdWE2TQ0KuQUfue04RTyHJe1f6BOj6c96s,1265
-source_google_sheets/manifest.yaml,sha256=HG8vpxv4lqwe5TCneq_zxuERaGNdtno7yAs61Wsk30E,15821
+source_google_sheets/manifest.yaml,sha256=CuSnA8dnRMeXWfyUA6aXBvGU3mz1dJIi0HqMiks9Fd0,15938
 source_google_sheets/models/__init__.py,sha256=Z-4MTpxG5t2jGhXzs4PPoIOa83zw3jRnUDx0N9Puv3s,61
 source_google_sheets/models/spreadsheet.py,sha256=DEef7bWQEpY1Uqyk7RN6qLF8oxLSNzuAtHlGRmMAKQA,1112
 source_google_sheets/models/spreadsheet_values.py,sha256=-XRMuuILn9JN8svHNTj6-oG8mLTZOZ5Hejy2pJ5bILk,440
 source_google_sheets/run.py,sha256=eaPRcarWqkB2b2DokvI83w7rz1blmWPQCFahvCyCdSY,1887
 source_google_sheets/source.py,sha256=qO1KoGdphieu7F5VgDYtrbqs56AUvMWFGNvFHP2b9Z4,778
 source_google_sheets/spec.yaml,sha256=mFOiMN1IsrjyLRcjTRw7xa0b74LwkUXdVvUqau7iTXc,5709
-source_google_sheets/utils.py,sha256=NUw8pJSCORGKx8mrhd11x4xS1dGUraDZdh6WxVn7aQw,5150
-airbyte_source_google_sheets-0.10.0.dev202505231635.dist-info/METADATA,sha256=MW6vZRfbucb1JqCsXRg2O93pL5s1hRalyUfVV-xKR6I,5385
-airbyte_source_google_sheets-0.10.0.dev202505231635.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-airbyte_source_google_sheets-0.10.0.dev202505231635.dist-info/entry_points.txt,sha256=Dtsfjohe5IPUFyqojk49SIoP7CifCTlNLG_pgivzppo,69
-airbyte_source_google_sheets-0.10.0.dev202505231635.dist-info/RECORD,,
+source_google_sheets/utils.py,sha256=4nr4MjdZa875qun2i8dyN2Y-B_QGjqShUPrvp4mJHec,5627
+airbyte_source_google_sheets-0.10.0.dev202506022219.dist-info/METADATA,sha256=NOT83ySAyrnrX7wr2Nm3FfH622KNxamaacHMb5WW64I,5385
+airbyte_source_google_sheets-0.10.0.dev202506022219.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+airbyte_source_google_sheets-0.10.0.dev202506022219.dist-info/entry_points.txt,sha256=Dtsfjohe5IPUFyqojk49SIoP7CifCTlNLG_pgivzppo,69
+airbyte_source_google_sheets-0.10.0.dev202506022219.dist-info/RECORD,,

source_google_sheets/manifest.yaml

@@ -224,11 +224,11 @@ definitions:
         path: >-
           {% if config["spreadsheet_id"] | regex_search("^(https://.*)") %}{{ config["spreadsheet_id"] | regex_search("/([-\\w]{20,})([/]?)") }}{% else %}{{ config["spreadsheet_id"] }}{% endif %}?includeGridData=true&ranges={{stream_partition.sheet_id | urlencode}}!1:1&alt=json
         error_handler:
-          type: CompositeErrorHandler
-          error_handlers:
-            - type: DefaultErrorHandler
-              response_filters:
-                $ref: "#/definitions/response_filters/single_sheet_response_error_filters"
+          type: DefaultErrorHandler
+          backoff_strategies:
+            - type: ExponentialBackoffStrategy
+          response_filters:
+            $ref: "#/definitions/response_filters/single_sheet_response_error_filters"
   response_filters:
     expected_one_sheet:
       type: HttpResponseFilter
@@ -320,9 +320,11 @@ definitions:
     single_sheet_response_error_filters:
       - $ref: "#/definitions/response_filters/expected_one_sheet"
       - $ref: "#/definitions/response_filters/ignore_duplicate_headers"
+      - $ref: "#/definitions/response_filters/rate_limit"
     check_operation_single_sheet_response_error_filters:
       - $ref: "#/definitions/response_filters/expected_one_sheet"
       - $ref: "#/definitions/response_filters/fail_duplicate_headers"
+      - $ref: "#/definitions/response_filters/rate_limit"
     response_error_filters:
       - $ref: "#/definitions/response_filters/server_error"
       - $ref: "#/definitions/response_filters/forbidden"

source_google_sheets/utils.py

@@ -39,57 +39,74 @@ def name_conversion(text: str) -> str:
 
 def experimental_name_conversion(text: str) -> str:
     """
-    Convert name using a set of rules, for example: '1MyName' -> '_1_my_name'
-    Removes leading/trailing spaces, combines number-word pairs (e.g., '50th' -> '50th'),
-    letter-number pairs (e.g., 'Q3' -> 'Q3'), and removes special characters without adding underscores.
-    Spaces are converted to underscores for snake_case.
+    Converts a string to a normalized, snake_case identifier for destination compatibility.
+
+    Checks Performed:
+      1. Removes leading and trailing spaces.
+         - Example: "EXAMPLE Domain " -> "example_domain"
+      2. Combines number-word pairs (e.g., "50th Percentile" -> "50th_percentile").
+      3. Removes all special characters (e.g., "Example ID*" -> "example_id").
+      4. Combines letter-number pairs (e.g., "Q3 2023" -> "q3_2023").
+      5. Preserves spaces between numbers and words as underscores.
+         - Example: "App Loading Milestone 1 (All)" -> "app_loading_milestone_1_all"
+      6. Handles sequences of special characters and spaces correctly, ensuring no extra or trailing underscores.
+         - Example: "Example (ID)" -> "example_id"
+
+    Additional Details:
+      - All output is lowercased.
+      - Digits are allowed at the start of the result in this version(e.g., "1MyName" -> "1my_name").
+      - Multiple spaces or special characters are collapsed/removed, not replaced with underscores.
+      - Only single underscores are used to separate tokens.
+
+    Examples:
+        "X9 D(a)ta" -> "x9_data"
+        "1MyName" -> "1my_name"
+        "Q3 2023" -> "q3_2023"
+        "EXAMPLE Domain " -> "example_domain"
+        "50th Percentile" -> "50th_percentile"
+        "Example ID*" -> "example_id"
+        "App Loading Milestone 1 (All)" -> "app_loading_milestone_1_all"
+        "Example (ID)" -> "example_id"
     """
-    text = unidecode.unidecode(text.strip())  # Strip leading/trailing spaces
+    # Remove all non-alphanumeric and non-space characters (symbols)
+    text = re.sub(r"[^\w\s]", "", text)
 
+    # Step 1: Tokenization
     tokens = []
     for m in TOKEN_PATTERN.finditer(text):
         if m.group("NoToken") is None:
             tokens.append(m.group(0))
         else:
-            # Only add an empty token for spaces to preserve snake_case; skip other special characters
-            if m.group(0).isspace():
-                tokens.append("")
-            # Otherwise, skip the special character entirely
+            # Process each character in NoToken match
+            for char in m.group(0):
+                if char.isspace():
+                    tokens.append("")
 
-    # Combine single uppercase letter followed by number (e.g., "Q" and "3" -> "Q3"), then number-word pairs
+    # Step 2: Combine adjacent tokens where appropriate
     combined_tokens = []
     i = 0
     while i < len(tokens):
-        # Check for letter-number pair (e.g., "Q3")
-        if i + 1 < len(tokens) and len(tokens[i]) == 1 and tokens[i].isupper() and tokens[i + 1].isdigit():
-            combined_tokens.append(tokens[i] + tokens[i + 1])
+        if i + 1 < len(tokens) and tokens[i] and len(tokens[i]) == 1 and tokens[i].isupper() and tokens[i + 1] and tokens[i + 1].isdigit():
+            combined_tokens.append(tokens[i] + tokens[i + 1])  # e.g., "Q3"
             i += 2
-        # Check for number-word pair (e.g., "50th")
-        elif i + 1 < len(tokens) and tokens[i].isdigit() and tokens[i + 1].isalpha():
-            combined_tokens.append(tokens[i] + tokens[i + 1])
+        elif i + 1 < len(tokens) and tokens[i] and tokens[i].isdigit() and tokens[i + 1] and tokens[i + 1].isalpha():
+            combined_tokens.append(tokens[i] + tokens[i + 1])  # e.g., "80th"
             i += 2
         else:
-            # Only add the token if it's non-empty to avoid underscores from spaces near special characters
-            if tokens[i]:
-                combined_tokens.append(tokens[i])
+            combined_tokens.append(tokens[i])
             i += 1
 
-    # Remove trailing empty tokens to avoid trailing underscores
-    while combined_tokens and combined_tokens[-1] == "":
-        combined_tokens.pop()
-    # Remove leading empty tokens to avoid leading underscores
+    # Step 3: Clean up empty tokens
     while combined_tokens and combined_tokens[0] == "":
         combined_tokens.pop(0)
-
+    while combined_tokens and combined_tokens[-1] == "":
+        combined_tokens.pop()
     if len(combined_tokens) >= 3:
         combined_tokens = combined_tokens[:1] + [t for t in combined_tokens[1:-1] if t] + combined_tokens[-1:]
 
-    if combined_tokens and combined_tokens[0].isdigit():
-        combined_tokens.insert(0, "")
-
-    text = DEFAULT_SEPARATOR.join(combined_tokens)
-    text = text.lower()
-    return text
+    # Step 4: Join and convert to lowercase
+    result = DEFAULT_SEPARATOR.join(combined_tokens)
+    return result.lower()
 
 
 def safe_name_conversion(text: str) -> str:
@@ -101,21 +118,12 @@ def safe_name_conversion(text: str) -> str:
     return new
 
 
-import csv
-
-
-def experimental_safe_name_conversion(text: str, output_file: str = "conversion_results2.csv") -> str:
+def experimental_safe_name_conversion(text: str) -> str:
     if not text:
         return text
     new = experimental_name_conversion(text)
     if not new:
         raise Exception(f"initial string '{text}' converted to empty")
-
-    # Write to CSV
-    with open(output_file, mode="a", newline="", encoding="utf-8") as file:
-        writer = csv.writer(file)
-        writer.writerow([text, new])  # Write the original and converted text
-
     return new