databricks-labs-lakebridge 0.10.1__tar.gz → 0.10.2__tar.gz

{databricks_labs_lakebridge-0.10.1 → databricks_labs_lakebridge-0.10.2}/PKG-INFO

@@ -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 → databricks_labs_lakebridge-0.10.2}/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-0.10.1 → databricks_labs_lakebridge-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-0.10.2/databricks/labs/lakebridge/helpers/string_utils.py

@@ -0,0 +1,28 @@
+def refactor_hexadecimal_chars(input_string: str) -> str:
+    """
+    Updates the HexaDecimal characters ( \x1b[\\d+m ) in the given string as below.
+    :param input_string: String with HexaDecimal characters. ex: ( \x1b[4mWHERE\x1b[0m )
+    :return: String with HexaDecimal characters refactored to arrows. ex: ( --> WHERE <--)
+    """
+    output_string = input_string
+    highlight = {"\x1b[4m": "--> ", "\x1b[0m": " <--"}
+    for key, value in highlight.items():
+        output_string = output_string.replace(key, value)
+    return output_string
+
+
+def format_error_message(error_type: str, error_message: Exception, error_sql: str) -> str:
+    """
+    Formats the error message with the error SQL.
+    :param error_type: Error Type
+    :param error_message: Error message
+    :param error_sql: Error SQL
+    :return: Formatted error message
+    """
+    error_str = (
+        f"------------------------ {error_type} Start:------------------------\n"
+        f"/*\n{str(error_message)}\n*/\n\n"
+        f"/*\nOriginal Query:\n\n{str(error_sql)}\n*/\n"
+        f"------------------------- {error_type} End:-------------------------"
+    ).strip()
+    return error_str

{databricks_labs_lakebridge-0.10.1 → databricks_labs_lakebridge-0.10.2}/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-0.10.1 → databricks_labs_lakebridge-0.10.2}/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-0.10.1 → databricks_labs_lakebridge-0.10.2}/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-0.10.2/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);

{databricks_labs_lakebridge-0.10.1 → databricks_labs_lakebridge-0.10.2}/pyproject.toml

@@ -29,9 +29,9 @@ classifiers = [
 dependencies = [
   "databricks-sdk~=0.51.0",
   "standard-distutils~=3.11.9; python_version>='3.11'",
-  "databricks-bb-analyzer~=0.1.7",
+  "databricks-bb-analyzer~=0.1.8",
   "sqlglot==26.1.3",
-  "databricks-labs-blueprint[yaml]>=0.11.0,<0.12.0",
+  "databricks-labs-blueprint[yaml]>=0.11.1,<0.12.0",
   "databricks-labs-lsql==0.16.0",
   "cryptography>=44.0.2,<45.1.0",
   "pyodbc~=5.2.0",

databricks_labs_lakebridge-0.10.1/databricks/labs/lakebridge/helpers/string_utils.py

@@ -1,62 +0,0 @@
-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.
-    :param input_string: String with HexaDecimal characters. ex: ( \x1b[4mWHERE\x1b[0m )
-    :return: String with HexaDecimal characters refactored to arrows. ex: ( --> WHERE <--)
-    """
-    output_string = input_string
-    highlight = {"\x1b[4m": "--> ", "\x1b[0m": " <--"}
-    for key, value in highlight.items():
-        output_string = output_string.replace(key, value)
-    return output_string
-
-
-def format_error_message(error_type: str, error_message: Exception, error_sql: str) -> str:
-    """
-    Formats the error message with the error SQL.
-    :param error_type: Error Type
-    :param error_message: Error message
-    :param error_sql: Error SQL
-    :return: Formatted error message
-    """
-    error_str = (
-        f"------------------------ {error_type} Start:------------------------\n"
-        f"/*\n{str(error_message)}\n*/\n\n"
-        f"/*\nOriginal Query:\n\n{str(error_sql)}\n*/\n"
-        f"------------------------- {error_type} End:-------------------------"
-    ).strip()
-    return error_str