databricks-labs-lakebridge 0.10.1__py3-none-any.whl → 0.10.2__py3-none-any.whl

databricks/labs/lakebridge/__about__.py

@@ -1,2 +1,2 @@
 # DO NOT MODIFY THIS FILE
-__version__ = "0.10.1"
+__version__ = "0.10.2"

databricks/labs/lakebridge/helpers/file_utils.py

@@ -51,14 +51,3 @@ def get_sql_file(input_path: str | Path) -> Generator[Path, None, None]:
         for filename in files:
             if is_sql_file(filename):
                 yield filename
-
-
-def read_file(filename: str | Path) -> str:
-    """
-    Reads the contents of the given file and returns it as a string.
-    :param filename: Input File Path
-    :return: File Contents as String
-    """
-    # pylint: disable=unspecified-encoding
-    with Path(filename).open() as file:
-        return file.read()

databricks/labs/lakebridge/helpers/string_utils.py

@@ -1,37 +1,3 @@
-import codecs
-
-
-# Optionally check to see if a string begins with a Byte Order Mark
-# such a character will cause the transpiler to fail
-def remove_bom(input_string: str) -> str:
-    """
-    Removes the Byte Order Mark (BOM) from the given string if it exists.
-    :param input_string: String to remove BOM from
-    :return: String without BOM
-    """
-    output_string = input_string
-
-    # Check and remove UTF-16 (LE and BE) BOM
-    if input_string.startswith(codecs.BOM_UTF16_BE.decode("utf-16-be")):
-        output_string = input_string[len(codecs.BOM_UTF16_BE.decode("utf-16-be")) :]
-    elif input_string.startswith(codecs.BOM_UTF16_LE.decode("utf-16-le")):
-        output_string = input_string[len(codecs.BOM_UTF16_LE.decode("utf-16-le")) :]
-    elif input_string.startswith(codecs.BOM_UTF16.decode("utf-16")):
-        output_string = input_string[len(codecs.BOM_UTF16.decode("utf-16")) :]
-    # Check and remove UTF-32 (LE and BE) BOM
-    elif input_string.startswith(codecs.BOM_UTF32_BE.decode("utf-32-be")):
-        output_string = input_string[len(codecs.BOM_UTF32_BE.decode("utf-32-be")) :]
-    elif input_string.startswith(codecs.BOM_UTF32_LE.decode("utf-32-le")):
-        output_string = input_string[len(codecs.BOM_UTF32_LE.decode("utf-32-le")) :]
-    elif input_string.startswith(codecs.BOM_UTF32.decode("utf-32")):
-        output_string = input_string[len(codecs.BOM_UTF32.decode("utf-32")) :]
-    # Check and remove UTF-8 BOM
-    elif input_string.startswith(codecs.BOM_UTF8.decode("utf-8")):
-        output_string = input_string[len(codecs.BOM_UTF8.decode("utf-8")) :]
-
-    return output_string
-
-
 def refactor_hexadecimal_chars(input_string: str) -> str:
     """
     Updates the HexaDecimal characters ( \x1b[\\d+m ) in the given string as below.

databricks/labs/lakebridge/intermediate/root_tables.py

@@ -1,11 +1,9 @@
 import logging
 from pathlib import Path
 
-from databricks.labs.lakebridge.helpers.file_utils import (
-    get_sql_file,
-    is_sql_file,
-    read_file,
-)
+from databricks.labs.blueprint.paths import read_text
+
+from databricks.labs.lakebridge.helpers.file_utils import get_sql_file, is_sql_file
 from databricks.labs.lakebridge.intermediate.dag import DAG
 
 from databricks.labs.lakebridge.transpiler.sqlglot.sqlglot_engine import SqlglotEngine
@@ -26,14 +24,14 @@ class RootTableAnalyzer:
         # when input is sql file then parse the file
         if is_sql_file(self.input_path):
             logger.debug(f"Generating Lineage file: {self.input_path}")
-            sql_content = read_file(self.input_path)
+            sql_content = read_text(self.input_path)
             self._populate_dag(sql_content, self.input_path, dag)
             return dag  # return after processing the file
 
         # when the input is a directory
         for path in get_sql_file(self.input_path):
             logger.debug(f"Generating Lineage file: {path}")
-            sql_content = read_file(path)
+            sql_content = read_text(path)
             self._populate_dag(sql_content, path, dag)
 
         return dag

databricks/labs/lakebridge/transpiler/execute.py

@@ -9,6 +9,7 @@ from typing import cast
 import itertools
 
 from databricks.labs.blueprint.installation import JsonObject
+from databricks.labs.blueprint.paths import read_text
 from databricks.labs.lakebridge.__about__ import __version__
 from databricks.labs.lakebridge.config import (
     TranspileConfig,
@@ -28,7 +29,6 @@ from databricks.labs.lakebridge.transpiler.transpile_status import (
     ErrorKind,
     ErrorSeverity,
 )
-from databricks.labs.lakebridge.helpers.string_utils import remove_bom
 from databricks.labs.lakebridge.helpers.validation import Validator
 from databricks.labs.lakebridge.transpiler.sqlglot.sqlglot_engine import SqlglotEngine
 from databricks.sdk import WorkspaceClient
@@ -62,15 +62,14 @@ async def _process_one_file(context: TranspilingContext) -> tuple[int, list[Tran
         )
         return 0, [error]
 
-    with context.input_path.open("r") as f:
-        source_code = remove_bom(f.read())
-        context = dataclasses.replace(context, source_code=source_code)
+    source_code = read_text(context.input_path)
+    context = dataclasses.replace(context, source_code=source_code)
 
     transpile_result = await _transpile(
         context.transpiler,
         str(context.config.source_dialect),
         context.config.target_dialect,
-        str(context.source_code),
+        source_code,
         context.input_path,
     )
 
@@ -158,7 +157,9 @@ def _process_single_result(context: TranspilingContext, error_list: list[Transpi
 
     output_path = cast(Path, context.output_path)
     with output_path.open("w") as w:
-        w.write(make_header(context.input_path, error_list))
+        # The above adds a java-style comment block at the top of the output file
+        # This would break .py or .json outputs so we disable it for now.
+        # w.write(make_header(context.input_path, error_list))
         w.write(output_code)
 
     logger.info(f"Processed file: {context.input_path} (errors: {len(error_list)})")

databricks/labs/lakebridge/transpiler/lsp/lsp_engine.py

@@ -523,9 +523,7 @@ class LSPEngine(TranspileEngine):
         self.close_document(file_path)
         return ChangeManager.apply(source_code, response.changes, response.diagnostics, file_path)
 
-    def open_document(self, file_path: Path, encoding="utf-8", source_code: str | None = None) -> None:
-        if source_code is None:
-            source_code = file_path.read_text(encoding)
+    def open_document(self, file_path: Path, source_code: str) -> None:
         text_document = TextDocumentItem(
             uri=file_path.as_uri(), language_id=LanguageKind.Sql, version=1, text=source_code
         )

{databricks_labs_lakebridge-0.10.1.dist-info → databricks_labs_lakebridge-0.10.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: databricks-labs-lakebridge
-Version: 0.10.1
+Version: 0.10.2
 Summary: Fast and predictable migrations to Databricks Lakehouse Platform. This tool is designed to help you migrate your data and workloads to the Databricks Lakehouse Platform in a fast, predictable, and reliable way. It provides a set of tools and utilities to help you reconcile your data and workloads, assess your current state, and plan your migration.
 Project-URL: Documentation, https://databrickslabs.github.io/lakebridge
 Project-URL: Issues, https://github.com/databrickslabs/lakebridge/issues
@@ -25,8 +25,8 @@ Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Utilities
 Requires-Python: >=3.10
 Requires-Dist: cryptography<45.1.0,>=44.0.2
-Requires-Dist: databricks-bb-analyzer~=0.1.7
-Requires-Dist: databricks-labs-blueprint[yaml]<0.12.0,>=0.11.0
+Requires-Dist: databricks-bb-analyzer~=0.1.8
+Requires-Dist: databricks-labs-blueprint[yaml]<0.12.0,>=0.11.1
 Requires-Dist: databricks-labs-lsql==0.16.0
 Requires-Dist: databricks-sdk~=0.51.0
 Requires-Dist: duckdb~=1.2.2

{databricks_labs_lakebridge-0.10.1.dist-info → databricks_labs_lakebridge-0.10.2.dist-info}/RECORD

@@ -2,11 +2,12 @@ docs/lakebridge/src/components/Button.tsx,sha256=5l_irZl4AGwK7k1e2rdOb_W2-305Q1m
 docs/lakebridge/src/css/custom.css,sha256=-XnDdVlHqJZXJmKarH7zCUMnnlAfpxIpZyr8FNJ4q0A,4024
 docs/lakebridge/src/css/table.css,sha256=_MAyY7hyhfFrSNVAvCA2QlqdbeBi4Kr9Ue93bSyhKSE,315
 docs/lakebridge/src/pages/index.tsx,sha256=fQRA9ZbKsPxZbXuSa1LMDk1xfYg2YXCFgsgzqus0NLc,1789
+docs/lakebridge/src/theme/DocSidebarItems/index.tsx,sha256=3FHRUOXJtjQk-caU_xAmmJWPC3E-H_ZZySV23tzqz3A,1334
 docs/lakebridge/src/theme/Footer/index.tsx,sha256=Jj8zY5WDiTLXwF_mAgld8Dh1A3MY1HFVVSYIoUs51so,1057
 docs/lakebridge/src/theme/Layout/index.tsx,sha256=IkdLr13jKmLxT0jWQqrwqrjVXc8Rwd_kWNpTd1t2sc0,592
 databricks/__init__.py,sha256=YqH8Hy8lHJxd0hLMZF6kWirUDdPiX90LRDX6S6yTMn0,261
 databricks/labs/__init__.py,sha256=YqH8Hy8lHJxd0hLMZF6kWirUDdPiX90LRDX6S6yTMn0,261
-databricks/labs/lakebridge/__about__.py,sha256=yME1bXdQJp7l83rLxzUY__9sQJos-JhiNDfB3KbW3WA,49
+databricks/labs/lakebridge/__about__.py,sha256=1jZlIfQdn0z-MHgWnSw-KUImADj-pX_Qj-zRbJOsOb8,49
 databricks/labs/lakebridge/__init__.py,sha256=nUNECqNvyfpT0aeWwlqG0ADT8U8ScCLb8WWpLydppcA,464
 databricks/labs/lakebridge/base_install.py,sha256=8NxXsNpgqXnuADKXVFh5oQL3osdvygRMY1amJwKfU08,490
 databricks/labs/lakebridge/cli.py,sha256=BgN1pz4dtLB_Y0C16_JhcRVxIfU7srZk24tUBSLJPAs,20597
@@ -45,16 +46,16 @@ databricks/labs/lakebridge/errors/exceptions.py,sha256=PIj8wRJpxrBXOLMMt9HQhBfhZ
 databricks/labs/lakebridge/helpers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 databricks/labs/lakebridge/helpers/db_sql.py,sha256=chFHpn6XIuC0GrJ3a30_Y7tcXd4KZ5qO9zCAI4d7TR0,806
 databricks/labs/lakebridge/helpers/execution_time.py,sha256=8oLEYh0AKz1fuiQMyDTWDymhxh6xUKlcFpINWzKnOy4,533
-databricks/labs/lakebridge/helpers/file_utils.py,sha256=rzZ0IBu7dlPNRtzLnzOv4sZZd2FBPPQNdodbkb3PQEI,1991
+databricks/labs/lakebridge/helpers/file_utils.py,sha256=0EISLVIleoKe0bzdvhd6RRWjbauX7eNB1eHSV9-2SIo,1676
 databricks/labs/lakebridge/helpers/metastore.py,sha256=1SKsIfNtiu3jUFjaXZ5B1fBZigVYqS1Q2OWhdn9qa8U,6425
 databricks/labs/lakebridge/helpers/recon_config_utils.py,sha256=1Nq_pIonE2tz08kdVpSDS-NVKGZ1p_kGRZBUQFFWZAs,7404
-databricks/labs/lakebridge/helpers/string_utils.py,sha256=_ovbMl7lXMKgYi1AF5UZQBcF1ZDs1PsSJV05erbEvg4,2786
+databricks/labs/lakebridge/helpers/string_utils.py,sha256=TKW0BHmOZ2G8EebCohQRJLYglqeJajHgQ2BLehf9qsE,1169
 databricks/labs/lakebridge/helpers/telemetry_utils.py,sha256=M0lqYcLdLKROnnu3KRJUlGS368IRPIACef4G1ae9cvA,435
 databricks/labs/lakebridge/helpers/validation.py,sha256=97AoCcsliWKUBKAY8SwgL4Dad-r_W59L_7h2I3Pudmk,4449
 databricks/labs/lakebridge/intermediate/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 databricks/labs/lakebridge/intermediate/dag.py,sha256=47bgyaYaBK_ELwLE5VGgFUraSxKdMJkLmo2lfc602lI,3165
 databricks/labs/lakebridge/intermediate/engine_adapter.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-databricks/labs/lakebridge/intermediate/root_tables.py,sha256=_3I0ks9qi9Al6HcURZ-gZ35IuP6dk7RUVuAOZHMcHp0,1497
+databricks/labs/lakebridge/intermediate/root_tables.py,sha256=G9PFU22qJ0BgV1FGZPK5bWNdEa8Xpo_gyEvMmATHkTw,1524
 databricks/labs/lakebridge/reconcile/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 databricks/labs/lakebridge/reconcile/compare.py,sha256=P9ABIT95TeS7BVRYVbzjpaEsynF2h2m5M8f9-he8A3A,16136
 databricks/labs/lakebridge/reconcile/constants.py,sha256=TrWuQFgSoBhRZkpiuscewG5eaZKV-FsErUQt4JO0cxo,798
@@ -145,11 +146,11 @@ databricks/labs/lakebridge/resources/reconcile/queries/installation/details.sql,
 databricks/labs/lakebridge/resources/reconcile/queries/installation/main.sql,sha256=s_A0YyGSX_pCWnQsQnY65VYFcbNvq2qKJvYxU6zam6E,794
 databricks/labs/lakebridge/resources/reconcile/queries/installation/metrics.sql,sha256=FdvjQp7gCwsbcu4UrOuJN-bBLJFpvUIyxH6PQvg04Wo,1006
 databricks/labs/lakebridge/transpiler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-databricks/labs/lakebridge/transpiler/execute.py,sha256=EOVAXHFzmfsS7cA5ogWKEUxGG6KokR-7PDZ8BdVwuz8,16871
+databricks/labs/lakebridge/transpiler/execute.py,sha256=IUlz682ptMndolCI7IIGRTXJpJnGXHaEZXZnCLdCEDA,16956
 databricks/labs/lakebridge/transpiler/transpile_engine.py,sha256=9o-MXAnCChbFxv9Kg8kGLXdc8BZmtlwV5JdMPiuTQNk,1827
 databricks/labs/lakebridge/transpiler/transpile_status.py,sha256=MO-Ju-ki3FCY15WxgwfPV9EC7Ma9q8aIfSTgHAmnkGU,1715
 databricks/labs/lakebridge/transpiler/lsp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-databricks/labs/lakebridge/transpiler/lsp/lsp_engine.py,sha256=6H12u41I6HxXqF8SII6janxXkT4GG9VcrsDFeOmA7Cg,22325
+databricks/labs/lakebridge/transpiler/lsp/lsp_engine.py,sha256=Whdb3Usi0_lq7i94c_D2XNXBTm-bfy3bso4nKIEq_qk,22205
 databricks/labs/lakebridge/transpiler/sqlglot/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 databricks/labs/lakebridge/transpiler/sqlglot/dialect_utils.py,sha256=GhXXWGA_2PlmHKjxrjryZpA5xaVZ81Vrw3b7DzjpFFI,1033
 databricks/labs/lakebridge/transpiler/sqlglot/lca_utils.py,sha256=vpDLGhE-wFMah1VTXkMg6gI_QnzdzpYZf0h9DUd8zcI,5154
@@ -163,9 +164,9 @@ databricks/labs/lakebridge/transpiler/sqlglot/parsers/presto.py,sha256=bY6Ku8ZPW
 databricks/labs/lakebridge/transpiler/sqlglot/parsers/snowflake.py,sha256=dZ7BdOlBZlkbiN9G9bu4l2c456265Gx9WoWUPRa7Ffg,23203
 databricks/labs/lakebridge/upgrades/v0.4.0_add_main_table_operation_name_column.py,sha256=wMTbj1q5td4fa5DCk0tWFJ-OmhhzsExRLYUe4PKmk0s,3527
 databricks/labs/lakebridge/upgrades/v0.6.0_alter_metrics_datatype.py,sha256=hnTHRtqzwPSF5Judzh6ss-uB5h3IFtm2ylWduwRNq5Y,2424
-databricks_labs_lakebridge-0.10.1.dist-info/METADATA,sha256=nGDYIxZ1D8NBXRz5ePlIUsulJHW-ljJ9QHdxhVZrqck,3078
-databricks_labs_lakebridge-0.10.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-databricks_labs_lakebridge-0.10.1.dist-info/entry_points.txt,sha256=Idr1CT73b8wShdr287yu1hheGbDbhBvucVUlZcbpiPo,75
-databricks_labs_lakebridge-0.10.1.dist-info/licenses/LICENSE,sha256=1hG0Cvw6mp9nL9qRoHFcCUk9fYqhcnj2vgJ75rt3BxA,3862
-databricks_labs_lakebridge-0.10.1.dist-info/licenses/NOTICE,sha256=wtxMsNvTkw1hAEkkWHz8A8JrYySAUSt1tOTcqddkWEg,1797
-databricks_labs_lakebridge-0.10.1.dist-info/RECORD,,
+databricks_labs_lakebridge-0.10.2.dist-info/METADATA,sha256=vZS_ckQImF3YDBo5xH0S3KXPOPn78Stn689GBu1dR-Q,3078
+databricks_labs_lakebridge-0.10.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+databricks_labs_lakebridge-0.10.2.dist-info/entry_points.txt,sha256=Idr1CT73b8wShdr287yu1hheGbDbhBvucVUlZcbpiPo,75
+databricks_labs_lakebridge-0.10.2.dist-info/licenses/LICENSE,sha256=1hG0Cvw6mp9nL9qRoHFcCUk9fYqhcnj2vgJ75rt3BxA,3862
+databricks_labs_lakebridge-0.10.2.dist-info/licenses/NOTICE,sha256=wtxMsNvTkw1hAEkkWHz8A8JrYySAUSt1tOTcqddkWEg,1797
+databricks_labs_lakebridge-0.10.2.dist-info/RECORD,,

docs/lakebridge/src/theme/DocSidebarItems/index.tsx

@@ -0,0 +1,42 @@
+import React, {memo, type ReactNode} from 'react';
+import {useLocation, useHistory} from 'react-router';
+import type {PropSidebarItem} from '@docusaurus/plugin-content-docs';
+import {
+  DocSidebarItemsExpandedStateProvider,
+  useVisibleSidebarItems,
+} from '@docusaurus/plugin-content-docs/client';
+import DocSidebarItem from '@theme/DocSidebarItem';
+
+import type {Props} from '@theme/DocSidebarItems';
+
+function DocSidebarItems({items, onItemClick, ...props}: Props): ReactNode {
+  const location = useLocation();
+  const history = useHistory();
+  const visibleItems = useVisibleSidebarItems(items, props.activePath);
+  
+  /**
+   * Additional logic for handling custom UI scenarios
+   */
+  const onClickHandler = (params: PropSidebarItem) => {
+    if (onItemClick) {
+      onItemClick(params);
+    }
+    
+    // show initial page on menu collapse
+    if (params.type === "category") {
+      if (location.pathname !== params.href && location.pathname.includes(params.href)) {
+        history.push(params.href);
+      }
+    }
+  }
+  
+  return (
+    <DocSidebarItemsExpandedStateProvider>
+      {visibleItems.map((item, index) => (
+        <DocSidebarItem key={index} item={item} index={index} {...props} onItemClick={onClickHandler} />
+      ))}
+    </DocSidebarItemsExpandedStateProvider>
+  );
+}
+
+export default memo(DocSidebarItems);