databricks-labs-lakebridge 0.10.1__py3-none-any.whl → 0.10.3__py3-none-any.whl

databricks/labs/lakebridge/config.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import logging
 from dataclasses import dataclass
 from enum import Enum, auto
@@ -31,11 +29,11 @@ class LSPConfigOptionV1:
     default: Any = None
 
     @classmethod
-    def parse_all(cls, data: dict[str, Any]) -> dict[str, list[LSPConfigOptionV1]]:
+    def parse_all(cls, data: dict[str, Any]) -> dict[str, list["LSPConfigOptionV1"]]:
         return {key: list(LSPConfigOptionV1.parse(item) for item in value) for (key, value) in data.items()}
 
     @classmethod
-    def parse(cls, data: Any) -> LSPConfigOptionV1:
+    def parse(cls, data: Any) -> "LSPConfigOptionV1":
         if not isinstance(data, dict):
             raise ValueError(f"Invalid transpiler config option, expecting a dict entry, got {data}")
         flag: str = data.get("flag", "")
@@ -79,7 +77,7 @@ class TranspileConfig:
     output_folder: str | None = None
     error_file_path: str | None = None
     sdk_config: dict[str, str] | None = None
-    skip_validation: bool | None = False
+    skip_validation: bool = False
     catalog_name: str = "remorph"
     schema_name: str = "transpiler"
     transpiler_options: JsonValue = None

databricks/labs/lakebridge/helpers/file_utils.py

@@ -1,3 +1,5 @@
+import contextlib
+import os
 from pathlib import Path
 from collections.abc import Generator
 
@@ -53,12 +55,11 @@ def get_sql_file(input_path: str | Path) -> Generator[Path, None, None]:
                 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()
+@contextlib.contextmanager
+def chdir(new_path: Path) -> Generator[None, None, None]:
+    saved_path = Path.cwd()
+    try:
+        os.chdir(new_path)
+        yield
+    finally:
+        os.chdir(saved_path)

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/install.py

@@ -37,6 +37,7 @@ from databricks.labs.lakebridge.config import (
 
 from databricks.labs.lakebridge.deployment.configurator import ResourceConfigurator
 from databricks.labs.lakebridge.deployment.installation import WorkspaceInstallation
+from databricks.labs.lakebridge.helpers.file_utils import chdir
 from databricks.labs.lakebridge.reconcile.constants import ReconReportType, ReconSourceType
 from databricks.labs.lakebridge.transpiler.lsp.lsp_engine import LSPConfig
 
@@ -251,12 +252,8 @@ class WheelInstaller(TranspilerInstaller):
         return self._post_install(version)
 
     def _create_venv(self) -> None:
-        cwd = os.getcwd()
-        try:
-            os.chdir(self._install_path)
+        with chdir(self._install_path):
             self._unsafe_create_venv()
-        finally:
-            os.chdir(cwd)
 
     def _unsafe_create_venv(self) -> None:
         # using the venv module doesn't work (maybe it's not possible to create a venv from a venv ?)
@@ -298,16 +295,12 @@ class WheelInstaller(TranspilerInstaller):
         raise ValueError(f"Could not locate 'site-packages' for {self._venv!s}")
 
     def _install_with_pip(self) -> None:
-        cwd = os.getcwd()
-        try:
-            os.chdir(self._install_path)
+        with chdir(self._install_path):
             # the way to call pip from python is highly sensitive to os and source type
             if self._artifact:
                 self._install_local_artifact()
             else:
                 self._install_remote_artifact()
-        finally:
-            os.chdir(cwd)
 
     def _install_local_artifact(self) -> None:
         pip = self._locate_pip()
@@ -557,10 +550,9 @@ class WorkspaceInstaller:
 
     @classmethod
     def install_morpheus(cls, artifact: Path | None = None):
-        java_version = cls.get_java_version()
-        if java_version is None or java_version < (11, 0, 0, 0):
-            logger.warning(
-                "This software requires Java 11 or above. Please install Java and re-run 'install-transpile'."
+        if not cls.is_java_version_okay():
+            logger.error(
+                "The morpheus transpiler requires Java 11 or above. Please install Java and re-run 'install-transpile'."
             )
             return
         product_name = "databricks-morph-plugin"
@@ -568,6 +560,26 @@ class WorkspaceInstaller:
         artifact_id = product_name
         TranspilerInstaller.install_from_maven(product_name, group_id, artifact_id, artifact)
 
+    @classmethod
+    def is_java_version_okay(cls) -> bool:
+        detected_java = cls.find_java()
+        match detected_java:
+            case None:
+                logger.warning("No Java executable found in the system PATH.")
+                return False
+            case (java_executable, None):
+                logger.warning(f"Java found, but could not determine the version: {java_executable}.")
+                return False
+            case (java_executable, bytes(raw_version)):
+                logger.warning(f"Java found ({java_executable}), but could not parse the version:\n{raw_version}")
+                return False
+            case (java_executable, tuple(old_version)) if old_version < (11, 0, 0, 0):
+                version_str = ".".join(str(v) for v in old_version)
+                logger.warning(f"Java found ({java_executable}), but version {version_str} is too old.")
+                return False
+            case _:
+                return True
+
     @classmethod
     def install_artifact(cls, artifact: str):
         path = Path(artifact)
@@ -582,25 +594,41 @@ class WorkspaceInstaller:
             logger.fatal(f"Cannot install unsupported artifact: {artifact}")
 
     @classmethod
-    def get_java_version(cls) -> tuple[int, int, int, int] | None:
+    def find_java(cls) -> tuple[Path, tuple[int, int, int, int] | bytes | None] | None:
+        """Locate Java and return its version, as reported by `java -version`.
+
+        The java executable is currently located by searching the system PATH. Its version is parsed from the output of
+        the `java -version` command, which has been standardized since Java 10.
+
+        Returns:
+            a tuple of its path and the version as a tuple of integers (feature, interim, update, patch), if the java
+            executable could be located. If the version cannot be parsed, instead the raw version information is
+            returned, or `None` as a last resort. When no java executable is found, `None` is returned instead of a
+            tuple.
+        """
         # Platform-independent way to reliably locate the java executable.
         # Reference: https://docs.python.org/3.10/library/subprocess.html#popen-constructor
         java_executable = shutil.which("java")
         if java_executable is None:
             return None
+        java_executable_path = Path(java_executable)
+        logger.debug(f"Using java executable: {java_executable_path!r}")
         try:
-            completed = run([java_executable, "-version"], shell=False, capture_output=True, check=True)
+            completed = run([str(java_executable_path), "-version"], shell=False, capture_output=True, check=True)
         except CalledProcessError as e:
             logger.debug(
                 f"Failed to run {e.args!r} (exit-code={e.returncode}, stdout={e.stdout!r}, stderr={e.stderr!r})",
                 exc_info=e,
             )
-            return None
+            return java_executable_path, None
         # It might not be ascii, but the bits we care about are so this will never fail.
-        java_version_output = completed.stderr.decode("ascii", errors="ignore")
+        raw_output = completed.stderr
+        java_version_output = raw_output.decode("ascii", errors="ignore")
         java_version = cls._parse_java_version(java_version_output)
+        if java_version is None:
+            return java_executable_path, raw_output.strip()
         logger.debug(f"Detected java version: {java_version}")
-        return java_version
+        return java_executable_path, java_version
 
     # Pattern to match a Java version string, compiled at import time to ensure it's valid.
     # Ref: https://docs.oracle.com/en/java/javase/11/install/version-string-format.html

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/reconcile/connectors/source_adapter.py

@@ -6,7 +6,7 @@ from databricks.labs.lakebridge.reconcile.connectors.data_source import DataSour
 from databricks.labs.lakebridge.reconcile.connectors.databricks import DatabricksDataSource
 from databricks.labs.lakebridge.reconcile.connectors.oracle import OracleDataSource
 from databricks.labs.lakebridge.reconcile.connectors.snowflake import SnowflakeDataSource
-from databricks.labs.lakebridge.reconcile.connectors.sql_server import SQLServerDataSource
+from databricks.labs.lakebridge.reconcile.connectors.tsql import TSQLServerDataSource
 from databricks.labs.lakebridge.transpiler.sqlglot.generator.databricks import Databricks
 from databricks.labs.lakebridge.transpiler.sqlglot.parsers.oracle import Oracle
 from databricks.labs.lakebridge.transpiler.sqlglot.parsers.snowflake import Snowflake
@@ -26,5 +26,5 @@ def create_adapter(
     if isinstance(engine, Databricks):
         return DatabricksDataSource(engine, spark, ws, secret_scope)
     if isinstance(engine, TSQL):
-        return SQLServerDataSource(engine, spark, ws, secret_scope)
+        return TSQLServerDataSource(engine, spark, ws, secret_scope)
     raise ValueError(f"Unsupported source type --> {engine}")

databricks/labs/lakebridge/reconcile/connectors/{sql_server.py → tsql.py}

@@ -47,7 +47,7 @@ _SCHEMA_QUERY = """SELECT
               """
 
 
-class SQLServerDataSource(DataSource, SecretsMixin, JDBCReaderMixin):
+class TSQLServerDataSource(DataSource, SecretsMixin, JDBCReaderMixin):
     _DRIVER = "sqlserver"
 
     def __init__(

databricks/labs/lakebridge/reconcile/constants.py

@@ -18,6 +18,7 @@ class ReconSourceType(AutoName):
     SNOWFLAKE = auto()
     ORACLE = auto()
     DATABRICKS = auto()
+    TSQL = auto()
 
 
 class ReconReportType(AutoName):

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,
     )
 
@@ -81,8 +80,9 @@ async def _process_one_file(context: TranspilingContext) -> tuple[int, list[Tran
     error_list = list(transpile_result.error_list)
     context = dataclasses.replace(context, transpiled_code=transpile_result.transpiled_code)
 
-    output_path = cast(Path, context.output_path)
-    output_path.parent.mkdir(parents=True, exist_ok=True)
+    output_path = context.output_path
+    assert output_path is not None, "Output path must be set in the context"
+    output_path.parent.mkdir(exist_ok=True)
 
     if _is_combined_result(transpile_result):
         _process_combined_result(context, error_list)
@@ -158,7 +158,9 @@ 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

@@ -35,7 +35,7 @@ from pygls.lsp.client import BaseLanguageClient
 from databricks.labs.blueprint.wheels import ProductInfo
 from databricks.labs.lakebridge.config import LSPConfigOptionV1, TranspileConfig, TranspileResult
 from databricks.labs.lakebridge.errors.exceptions import IllegalStateException
-from databricks.labs.lakebridge.helpers.file_utils import is_sql_file, is_dbt_project_file
+from databricks.labs.lakebridge.helpers.file_utils import chdir, is_dbt_project_file, is_sql_file
 from databricks.labs.lakebridge.transpiler.transpile_engine import TranspileEngine
 from databricks.labs.lakebridge.transpiler.transpile_status import (
     CodePosition,
@@ -389,6 +389,14 @@ class LSPEngine(TranspileEngine):
         self._client = _LanguageClient(name, version)
         self._init_response: InitializeResult | None = None
 
+    @property
+    def transpiler_name(self) -> str:
+        return self._config.name
+
+    def options_for_dialect(self, source_dialect: str) -> list[LSPConfigOptionV1]:
+        """Get the options supported when transpiling a given source dialect."""
+        return self._config.options_for_dialect(source_dialect)
+
     @property
     def supported_dialects(self) -> list[str]:
         return self._config.remorph.dialects
@@ -400,15 +408,14 @@ class LSPEngine(TranspileEngine):
     async def initialize(self, config: TranspileConfig) -> None:
         if self.is_alive:
             raise IllegalStateException("LSP engine is already initialized")
-        cwd = os.getcwd()
         try:
-            os.chdir(self._workdir)
-            await self._do_initialize(config)
+            # TODO: Avoid this by setting the working directory when launching the child process.
+            with chdir(self._workdir):
+                await self._do_initialize(config)
             await self._await_for_transpile_capability()
         # it is good practice to catch broad exceptions raised by launching a child process
         except Exception as e:  # pylint: disable=broad-exception-caught
             logger.error("LSP initialization failed", exc_info=e)
-            os.chdir(cwd)
 
     async def _do_initialize(self, config: TranspileConfig) -> None:
         await self._start_server()
@@ -523,9 +530,7 @@ 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/transpiler/sqlglot/sqlglot_engine.py

@@ -39,6 +39,10 @@ class SqlglotEngine(TranspileEngine):
     def supported_dialects(self) -> list[str]:
         return sorted(SQLGLOT_DIALECTS.keys())
 
+    @property
+    def transpiler_name(self) -> str:
+        return "sqlglot"
+
     def _partial_transpile(
         self,
         read_dialect: Dialect,

databricks/labs/lakebridge/transpiler/transpile_engine.py

@@ -37,13 +37,11 @@ class TranspileEngine(abc.ABC):
 
     @property
     @abc.abstractmethod
-    def supported_dialects(self) -> list[str]: ...
+    def transpiler_name(self) -> str: ...
 
-    def check_source_dialect(self, source_dialect: str | None) -> None:
-        if source_dialect not in self.supported_dialects:
-            raise ValueError(
-                f"Invalid value for '--source-dialect': '{source_dialect}' is not one of {self.supported_dialects}."
-            )
+    @property
+    @abc.abstractmethod
+    def supported_dialects(self) -> list[str]: ...
 
     @abc.abstractmethod
     def is_supported_file(self, file: Path) -> bool: ...

{databricks_labs_lakebridge-0.10.1.dist-info → databricks_labs_lakebridge-0.10.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: databricks-labs-lakebridge
-Version: 0.10.1
+Version: 0.10.3
 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~=0.1.9
+Requires-Dist: databricks-labs-blueprint[yaml]<0.12.0,>=0.11.2
 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-0.10.3.dist-info}/RECORD

@@ -1,17 +1,19 @@
 docs/lakebridge/src/components/Button.tsx,sha256=5l_irZl4AGwK7k1e2rdOb_W2-305Q1mjwXA3iP8CqaM,3159
+docs/lakebridge/src/components/ReconcileTabs.tsx,sha256=xJD0nq_raoYv70YLEnG2iuAUTSXXvDpmtmjX7X9Tw9E,2665
 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=LBCN0OI_6vUqxgIo75HVdQc1TP5LOmy5HIs3OKrDIpk,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
-databricks/labs/lakebridge/config.py,sha256=Kxl_Yzo5ooiFrt95Gp7AwyLlPZopa4MmQKpBfpHso2Y,5872
-databricks/labs/lakebridge/install.py,sha256=e7MdIWFHHr2-sp-NNe6inJ44s_jgL-b_g_Y4MJXtqNQ,38724
+databricks/labs/lakebridge/cli.py,sha256=6exPUJs7c2qVo-X9VXFg5VM3XqOCdlk0_5OXfPw6nbY,31578
+databricks/labs/lakebridge/config.py,sha256=IjxvphM9fRQHQ2FAxwZ23deJGgSemJ3rMV0sp1Ob6e8,5833
+databricks/labs/lakebridge/install.py,sha256=EmtzbC-pOeiK7lqn4wxSRoeODlkqB_lQBJ9Mj4E0kjE,40536
 databricks/labs/lakebridge/jvmproxy.py,sha256=F9pXpemzdaJXwpshHxVM9PYU_eNn4zTCUFQ5vc9WIhA,1573
 databricks/labs/lakebridge/lineage.py,sha256=Q2oky4RkODRHWMwIQIwbYXSdZTmRkMWwEh6RssBiQxY,1843
 databricks/labs/lakebridge/uninstall.py,sha256=hf36YgeW9XO2cRvvn6AXUZdihQ1ZMHnR38OVEF5sfRw,759
@@ -45,19 +47,19 @@ 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=1X3ri7_kyZibOFq36mX8fiERhE3tru_7VZIat1jjzOc,1911
 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
+databricks/labs/lakebridge/reconcile/constants.py,sha256=ZXhGp0hxNdCWTN0iOfaIiDvRkxMZm4E7vtL-tVDsImM,816
 databricks/labs/lakebridge/reconcile/exception.py,sha256=kA-1KVAgZfWzxhcUwYha_8OapmFajJG0iY5TxPUPJyQ,1463
 databricks/labs/lakebridge/reconcile/execute.py,sha256=13yDonKuOcGytIDEySgAF--8VC_zLR4-hLudD2EkE0g,35111
 databricks/labs/lakebridge/reconcile/recon_capture.py,sha256=mlrKSzeTQnq3_ncbTunE1OyIFA2bLKlwiuDMicQRf5c,27317
@@ -73,8 +75,8 @@ databricks/labs/lakebridge/reconcile/connectors/jdbc_reader.py,sha256=SsY1rkeLo4
 databricks/labs/lakebridge/reconcile/connectors/oracle.py,sha256=LBqlK5WbgB4XaQNJ_DomTHXazdHJNu4vkIic_z6UENw,4795
 databricks/labs/lakebridge/reconcile/connectors/secrets.py,sha256=vue72BaYVaaeUfTOaqIEwP-I3TApgbPiuq69Z6I2u3k,1125
 databricks/labs/lakebridge/reconcile/connectors/snowflake.py,sha256=ARooTfPo6Vvrrj1n3KQ6aW-raAkoY_Z_qHB6epa5WVI,8086
-databricks/labs/lakebridge/reconcile/connectors/source_adapter.py,sha256=N_qbIuJsU7q3M3WWLv36DTKH-zYqV7js7Vcdx9Z7fLo,1449
-databricks/labs/lakebridge/reconcile/connectors/sql_server.py,sha256=vvjNyw8ZhO-IqMMCuSVcD19vPOrWTh2WH5ndoxKybHE,5675
+databricks/labs/lakebridge/reconcile/connectors/source_adapter.py,sha256=I6LBE0C8e80lMm_lVBVIrW9g9ogIgZ53J_EFRNkcSWY,1445
+databricks/labs/lakebridge/reconcile/connectors/tsql.py,sha256=71ChvUvDWSp6qftl4cJ7B_ztnchpU7uXo1_zLl5cDbc,5676
 databricks/labs/lakebridge/reconcile/query_builder/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 databricks/labs/lakebridge/reconcile/query_builder/aggregate_query.py,sha256=zCPmLBLWeKwn0E2QMs0ua2CIJ6cnxmn77mNt4lvauTw,13783
 databricks/labs/lakebridge/reconcile/query_builder/base.py,sha256=J1LSemcN6bn-0K5U1PhXaQj22axOmqHUv-s9WwLQZOk,5293
@@ -145,16 +147,16 @@ 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/transpile_engine.py,sha256=9o-MXAnCChbFxv9Kg8kGLXdc8BZmtlwV5JdMPiuTQNk,1827
+databricks/labs/lakebridge/transpiler/execute.py,sha256=7DpeIixATOPryyt4TD93-sdwE1C_fIwuo6bKwClaF_s,17007
+databricks/labs/lakebridge/transpiler/transpile_engine.py,sha256=5zC8fkpBBlt9RjE_BeA_Sd6vaRxA3mBdhTqoRGFTc_Y,1616
 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=osT4RXpYqBNcAQ8mcoFt8m2dygs5TcmYnQq57KN_kw4,22580
 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
 databricks/labs/lakebridge/transpiler/sqlglot/local_expression.py,sha256=V69eEJHyZKxmyaham6OulYnwQRqkbGUrdiWm1EWP8YE,3825
-databricks/labs/lakebridge/transpiler/sqlglot/sqlglot_engine.py,sha256=3-YTEDPCk3Q7nT6A09D0p_IH8ftC3wr4sPF23Yy_OJM,10053
+databricks/labs/lakebridge/transpiler/sqlglot/sqlglot_engine.py,sha256=1uqpYIB-6vhuFqco80lXyBqqdkVkZkk9xuqFAvf2kXI,10131
 databricks/labs/lakebridge/transpiler/sqlglot/generator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 databricks/labs/lakebridge/transpiler/sqlglot/generator/databricks.py,sha256=tF38z3J-P0mDnGeDmCzAiowAUoShiosimM6nfR_-3Ro,30653
 databricks/labs/lakebridge/transpiler/sqlglot/parsers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -163,9 +165,9 @@ 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-0.10.3.dist-info/METADATA,sha256=e7yr--8po1oLKE8_BRRTFbv_y2fJ0Fw5F95wT2bnn8U,3078
+databricks_labs_lakebridge-0.10.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+databricks_labs_lakebridge-0.10.3.dist-info/entry_points.txt,sha256=Idr1CT73b8wShdr287yu1hheGbDbhBvucVUlZcbpiPo,75
+databricks_labs_lakebridge-0.10.3.dist-info/licenses/LICENSE,sha256=1hG0Cvw6mp9nL9qRoHFcCUk9fYqhcnj2vgJ75rt3BxA,3862
+databricks_labs_lakebridge-0.10.3.dist-info/licenses/NOTICE,sha256=wtxMsNvTkw1hAEkkWHz8A8JrYySAUSt1tOTcqddkWEg,1797
+databricks_labs_lakebridge-0.10.3.dist-info/RECORD,,

docs/lakebridge/src/components/ReconcileTabs.tsx

@@ -0,0 +1,86 @@
+import React, {useRef,useEffect} from 'react';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import useBaseUrl from '@docusaurus/useBaseUrl';
+
+type FrameTabProps = {
+    src: string;
+    label: string;
+};
+
+const frameStyle: React.CSSProperties = {
+    width: '100%',
+    height: '500px',
+    border: '1px solid #ccc',
+    borderRadius: '6px',
+    marginBottom: '1em',
+    overflow: 'auto',
+};
+
+const FrameTab: React.FC<FrameTabProps> = ({ src, label }) => {
+    const iframeRef = useRef<HTMLIFrameElement>(null);
+    const url = useBaseUrl(src);
+
+    useEffect(() => {
+        const iframe = iframeRef.current;
+        if (!iframe) return;
+
+        const onLoad = () => {
+            try {
+                const doc = iframe.contentDocument || iframe.contentWindow?.document;
+                if (!doc) return;
+
+                const elementsToRemove = doc.querySelectorAll(
+                    'div[data-testid="content-spacer"], div[data-testid="extra-whitespace"]'
+                );
+
+                elementsToRemove.forEach(el => {
+                    if (!el.children.length) {
+                        el.remove();
+                    }
+                });
+            } catch (err) {
+                console.warn(err);
+            }
+        };
+
+        iframe.addEventListener('load', onLoad);
+
+        return () => {
+            iframe.removeEventListener('load', onLoad);
+        };
+    }, [url]);
+
+    return (
+        <div>
+            <div style={{ marginBottom: '0.5em' }}>
+                <a href={url} target="_blank" rel="noopener noreferrer">
+                    Open notebook in new tab
+                </a>
+            </div>
+            <iframe ref={iframeRef} src={url} style={frameStyle} title={label} />
+        </div>
+    );
+};
+
+const LakebridgeTabs: React.FC = () => (
+    <Tabs>
+        {/*        <TabItem value="Readme" label="Readme" default>
+            <FrameTab src="/lakebridge_reconcile/Readme.html" label="Readme" />
+        </TabItem>*/}
+        <TabItem value="Recon Main" label="Recon Main">
+            <FrameTab src="/lakebridge_reconcile/lakebridge_recon_main.html" label="Recon Main" />
+        </TabItem>
+        <TabItem value="Recon Wrapper" label="Recon Wrapper">
+            <FrameTab src="/lakebridge_reconcile/recon_wrapper_nb.html" label="Recon Wrapper" />
+        </TabItem>
+        <TabItem value="Snowflake Example" label="Transformation Query Generator">
+            <FrameTab
+                src="/lakebridge_reconcile/snowflake_transformation_query_generator.html"
+                label="Query Generator"
+            />
+        </TabItem>
+    </Tabs>
+);
+
+export default LakebridgeTabs;