cdmduck 0.0.1__tar.gz

cdmduck-0.0.1/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cdmduck-0.0.1/NOTICE

@@ -0,0 +1,9 @@
+cdmduck
+Copyright 2026 cdmduck authors
+
+This product includes software and data derived from OHDSI SqlRender
+(https://github.com/OHDSI/SqlRender), Copyright Observational Health Data
+Sciences and Informatics, licensed under the Apache License, Version 2.0:
+  - src/cdmduck/sqlrender (Python port of org.ohdsi.sql.*)
+  - src/cdmduck/sqlrender/csv/replacementPatterns.csv (verbatim)
+  - ref/java, tests/java/org (verbatim Java reference sources)

cdmduck-0.0.1/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: cdmduck
+Version: 0.0.1
+Summary: OMOP CDM / OHDSI ATLAS-compatible tools on DuckDB: SqlRender, Circe and a WebAPI-compatible server in pure Python
+Author-email: Hyung-Chul Lee <lucid80@gmail.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/vitaldb/cdmduck
+Project-URL: Source, https://github.com/vitaldb/cdmduck
+Keywords: omop,cdm,ohdsi,atlas,sqlrender,circe,duckdb
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Healthcare Industry
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Provides-Extra: server
+Requires-Dist: duckdb>=1.0; extra == "server"
+Requires-Dist: fastapi; extra == "server"
+Requires-Dist: uvicorn; extra == "server"
+Dynamic: license-file
+
+<p align="center"><img src="https://raw.githubusercontent.com/vitaldb/cdmduck/main/docs/logo.png" alt="cdmduck" width="320"></p>
+
+# cdmduck
+
+**OMOP data. Simpler. Faster. Everywhere.** — OHDSI ATLAS-compatible tools for the OMOP CDM,
+in pure Python on DuckDB. No Java, no Postgres, no Docker.
+
+OMOP CDM · OHDSI ATLAS 호환 도구를 DuckDB 위에서, 순수 파이썬으로.
+
+```
+pip install cdmduck
+```
+
+| 모듈 | 원본 (OHDSI, Apache 2.0) | 상태 |
+|---|---|---|
+| `cdmduck.sqlrender` | SqlRender (Java) | 이식 완료 — Java 판과 58,440 건 글자 단위 일치 |
+| `cdmduck.circe` | circe-be (Java) | 예정 |
+| `cdmduck.webapi` | WebAPI 3.0 (Java) — ATLAS 3.0 화면이 부르는 API | 예정 |
+
+```python
+from cdmduck.sqlrender import render, translate
+sql = render("SELECT TOP 10 * FROM @cdm.person {@adult}?{WHERE year_of_birth < 2000};", cdm="main", adult=True)
+translate(sql, "duckdb")   # SELECT  * FROM main.person WHERE year_of_birth < 2000 LIMIT 10;
+```
+
+```
+cdmduck translate query.sql duckdb -p cdm=main
+cdmduck dialects
+```
+
+## Java 판과의 동등성 검증
+
+`tests/equiv/` — SqlRender R 테스트 문자열 2,009개, Circe·WebAPI SQL 763개(×16 방언·렌더·분할),
+합성 조건식 3,000개를 Java 원본(`tests/java`, JDK 22+ 소스 실행)과 이 이식본에 넣어 결과를 비교한다.
+
+```
+python3 tests/equiv/build_corpus.py <클론 디렉터리> cases.tsv
+python3 tests/equiv/run_java.py cases.tsv java.out 24
+PYTHONPATH=src python3 tests/equiv/py_harness.py cases.tsv py.out 32
+python3 tests/equiv/diff.py cases.tsv java.out py.out
+```
+
+알려진 차이: Java 내부 예외(EmptyStack, ArrayIndexOutOfBounds)의 메시지 문구만 다르다(예외가 나는 자리는 같다).
+BMP 밖 문자(이모지 등)는 Java 가 UTF-16 대리쌍 둘로 보므로 위치가 달라질 수 있다.
+
+## 라이선스
+
+Apache 2.0. `src/cdmduck/sqlrender/csv/replacementPatterns.csv` 와 `ref/java`, `tests/java/org` 는
+OHDSI SqlRender 에서 가져왔다(`third_party/`, `NOTICE`).

cdmduck-0.0.1/README.md

@@ -0,0 +1,49 @@
+<p align="center"><img src="https://raw.githubusercontent.com/vitaldb/cdmduck/main/docs/logo.png" alt="cdmduck" width="320"></p>
+
+# cdmduck
+
+**OMOP data. Simpler. Faster. Everywhere.** — OHDSI ATLAS-compatible tools for the OMOP CDM,
+in pure Python on DuckDB. No Java, no Postgres, no Docker.
+
+OMOP CDM · OHDSI ATLAS 호환 도구를 DuckDB 위에서, 순수 파이썬으로.
+
+```
+pip install cdmduck
+```
+
+| 모듈 | 원본 (OHDSI, Apache 2.0) | 상태 |
+|---|---|---|
+| `cdmduck.sqlrender` | SqlRender (Java) | 이식 완료 — Java 판과 58,440 건 글자 단위 일치 |
+| `cdmduck.circe` | circe-be (Java) | 예정 |
+| `cdmduck.webapi` | WebAPI 3.0 (Java) — ATLAS 3.0 화면이 부르는 API | 예정 |
+
+```python
+from cdmduck.sqlrender import render, translate
+sql = render("SELECT TOP 10 * FROM @cdm.person {@adult}?{WHERE year_of_birth < 2000};", cdm="main", adult=True)
+translate(sql, "duckdb")   # SELECT  * FROM main.person WHERE year_of_birth < 2000 LIMIT 10;
+```
+
+```
+cdmduck translate query.sql duckdb -p cdm=main
+cdmduck dialects
+```
+
+## Java 판과의 동등성 검증
+
+`tests/equiv/` — SqlRender R 테스트 문자열 2,009개, Circe·WebAPI SQL 763개(×16 방언·렌더·분할),
+합성 조건식 3,000개를 Java 원본(`tests/java`, JDK 22+ 소스 실행)과 이 이식본에 넣어 결과를 비교한다.
+
+```
+python3 tests/equiv/build_corpus.py <클론 디렉터리> cases.tsv
+python3 tests/equiv/run_java.py cases.tsv java.out 24
+PYTHONPATH=src python3 tests/equiv/py_harness.py cases.tsv py.out 32
+python3 tests/equiv/diff.py cases.tsv java.out py.out
+```
+
+알려진 차이: Java 내부 예외(EmptyStack, ArrayIndexOutOfBounds)의 메시지 문구만 다르다(예외가 나는 자리는 같다).
+BMP 밖 문자(이모지 등)는 Java 가 UTF-16 대리쌍 둘로 보므로 위치가 달라질 수 있다.
+
+## 라이선스
+
+Apache 2.0. `src/cdmduck/sqlrender/csv/replacementPatterns.csv` 와 `ref/java`, `tests/java/org` 는
+OHDSI SqlRender 에서 가져왔다(`third_party/`, `NOTICE`).

cdmduck-0.0.1/pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cdmduck"
+version = "0.0.1"
+description = "OMOP CDM / OHDSI ATLAS-compatible tools on DuckDB: SqlRender, Circe and a WebAPI-compatible server in pure Python"
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.8"
+authors = [{ name = "Hyung-Chul Lee", email = "lucid80@gmail.com" }]
+keywords = ["omop", "cdm", "ohdsi", "atlas", "sqlrender", "circe", "duckdb"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Healthcare Industry",
+  "Intended Audience :: Science/Research",
+  "Programming Language :: Python :: 3",
+  "Topic :: Database",
+  "Topic :: Scientific/Engineering :: Medical Science Apps.",
+]
+dependencies = []
+
+[project.urls]
+Homepage = "https://github.com/vitaldb/cdmduck"
+Source = "https://github.com/vitaldb/cdmduck"
+
+[project.optional-dependencies]
+server = ["duckdb>=1.0", "fastapi", "uvicorn"]
+
+[project.scripts]
+cdmduck = "cdmduck.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+"cdmduck.sqlrender" = ["csv/*.csv"]

cdmduck-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

cdmduck-0.0.1/src/cdmduck/__init__.py

@@ -0,0 +1,2 @@
+"""cdmduck — OMOP CDM · OHDSI ATLAS 호환 도구를 DuckDB 위에서, 순수 파이썬으로."""
+__version__ = '0.0.1'

cdmduck-0.0.1/src/cdmduck/cli.py

@@ -0,0 +1,28 @@
+"""명령어 `cdmduck`."""
+import argparse
+import sys
+
+
+def main(argv=None):
+    ap = argparse.ArgumentParser(prog='cdmduck', description='OMOP CDM / ATLAS-compatible tools on DuckDB')
+    sub = ap.add_subparsers(dest='cmd', required=True)
+    t = sub.add_parser('translate', help='SQL Server 방언 SQL 을 대상 방언으로 번역')
+    t.add_argument('file', help="SQL 파일 ('-' 는 표준입력)")
+    t.add_argument('dialect')
+    t.add_argument('--temp-schema')
+    t.add_argument('-p', '--param', action='append', default=[], metavar='KEY=VALUE', help='번역 전에 렌더할 파라미터')
+    sub.add_parser('dialects', help='지원 방언 목록')
+    a = ap.parse_args(argv)
+    from .sqlrender import dialects, render, translate
+    if a.cmd == 'dialects':
+        print('\n'.join(dialects()))
+    elif a.cmd == 'translate':
+        sql = sys.stdin.read() if a.file == '-' else open(a.file, encoding='utf-8').read()
+        if a.param:
+            sql = render(sql, **dict(p.split('=', 1) for p in a.param))
+        sys.stdout.write(translate(sql, a.dialect, temp_emulation_schema=a.temp_schema))
+    return 0
+
+
+if __name__ == '__main__':
+    sys.exit(main())

cdmduck-0.0.1/src/cdmduck/sqlrender/__init__.py

@@ -0,0 +1,37 @@
+"""OHDSI SqlRender 의 파이썬 이식 — Java 판과 출력이 글자 단위로 같도록 맞춘다.
+
+    from cdmduck.sqlrender import render, translate
+    sql = render("SELECT * FROM @cdm.person {@limit}?{LIMIT 10}", cdm="main", limit=True)
+    sql = translate(sql, "duckdb")
+"""
+from ._java import JavaError
+from ._render import check as check_render
+from ._render import render_sql
+from ._strings import split_sql
+from ._translate import (check as check_translate, dialects, generate_session_id, set_replacement_patterns,
+                         translate_single_statement_sql, translate_sql)
+
+__all__ = ['render', 'translate', 'translate_single_statement', 'split_sql', 'render_sql', 'translate_sql',
+           'translate_single_statement_sql', 'dialects', 'generate_session_id', 'set_replacement_patterns',
+           'check_render', 'check_translate', 'JavaError']
+
+
+def _value(v):
+    """R SqlRender 와 같은 값 변환: 논리값은 TRUE/FALSE, 목록은 쉼표로 잇는다."""
+    if isinstance(v, bool):
+        return 'TRUE' if v else 'FALSE'
+    if isinstance(v, (list, tuple, set)):
+        return ','.join(_value(x) for x in v)
+    return str(v)
+
+
+def render(sql, **params):
+    return render_sql(sql, list(params), [_value(v) for v in params.values()])
+
+
+def translate(sql, target_dialect, temp_emulation_schema=None, session_id=None):
+    return translate_sql(sql, target_dialect, session_id, temp_emulation_schema)
+
+
+def translate_single_statement(sql, target_dialect, temp_emulation_schema=None, session_id=None):
+    return translate_single_statement_sql(sql, target_dialect, session_id, temp_emulation_schema)

cdmduck-0.0.1/src/cdmduck/sqlrender/_bigquery_spark.py

@@ -0,0 +1,207 @@
+"""org.ohdsi.sql.BigQuerySparkTranslate 포팅 (DB 연결이 필요한 sparkHandleInsert 는 제외)."""
+import re
+
+from ._java import JavaError, split, substring, trim
+from ._strings import split_sql, tokenize_sql
+from ._translate import parse_search_pattern, search
+
+SELECT, GROUP_BY, ORDER_BY, WITH_COLUMNS, IN = range(5)
+
+
+class _CommaListIterator:
+    def __init__(self, expression_list, list_type):
+        self.list_type = list_type
+        self.expression_list = expression_list
+        self._split_list()
+        self.expression_list = ',' + self.expression_list + ','
+        self.pattern = parse_search_pattern(', @@a ,')
+        self.cur = search(self.expression_list, self.pattern, 0)
+        if self.cur.start != -1:
+            self._split_expression()
+
+    def done(self):
+        return self.cur.start == -1
+
+    def next(self):
+        n = len(tokenize_sql(substring(self.expression_list, self.cur.start, self.cur.end)))
+        self.cur = search(self.expression_list, self.pattern, self.cur.start_token + n - 1)
+        if self.cur.start != -1:
+            self._split_expression()
+
+    def full(self):
+        return _s(self.prefix) + _s(self.suffix)
+
+    def _split_list(self):
+        self.list_prefix = ''
+        self.list_suffix = ''
+        if self.list_type == SELECT:
+            m = search('^' + _s(self.expression_list) + '$', parse_search_pattern('^ distinct @@a $'), 0)
+            if m.start != -1:
+                self.list_prefix = 'distinct '
+                self.expression_list = m.variable_to_value.get('@@a')
+            m = search('^' + _s(self.expression_list) + '$', parse_search_pattern('^@@a into @@b$'), 0)
+            if m.start != -1:
+                self.expression_list = m.variable_to_value.get('@@a')
+                self.list_suffix = ' into ' + _s(m.variable_to_value.get('@@b'))
+        elif self.list_type == GROUP_BY:
+            m = search('^' + _s(self.expression_list) + '$', parse_search_pattern('^@@a order by @@b$'), 0)
+            if m.start != -1:
+                self.expression_list = m.variable_to_value.get('@@a')
+                self.list_suffix = ' order by ' + _s(m.variable_to_value.get('@@b'))
+
+    def _split_expression(self):
+        self.prefix = self.cur.variable_to_value.get('@@a')
+        self.suffix = ''
+        if self.list_type == SELECT:
+            self._split_alias()
+        elif self.list_type == ORDER_BY:
+            tokens = tokenize_sql(self.full())
+            if not tokens:
+                raise JavaError('IndexOutOfBoundsException')
+            last = tokens[-1]
+            if last.text.lower() in ('asc', 'desc'):
+                self.prefix = substring(self.full(), 0, last.start - 1)
+                self.suffix = ' ' + last.text
+
+    def _split_alias(self):
+        tokens = tokenize_sql(self.prefix)
+        m = search('^' + self.prefix + '$', parse_search_pattern('^ @@a as @@b $'), 0)
+        if m.start == -1:
+            if len(tokens) >= 2:
+                alias = tokens[-1]
+                preceding = tokens[-2].text
+                if alias.is_identifier() and preceding != '.' and preceding != '+':
+                    self.prefix = substring(self.prefix, 0, alias.start)
+                    self.suffix = alias.text
+        else:
+            self.prefix = m.variable_to_value.get('@@a')
+            self.suffix = m.variable_to_value.get('@@b')
+
+    def is_single_column_reference(self):
+        t = tokenize_sql(self.prefix)
+        return len(t) == 3 and t[0].is_identifier() and t[1].text == '.' and t[2].is_identifier()
+
+
+def _s(x):
+    """Java 문자열 연결: null 은 "null"."""
+    return 'null' if x is None else x
+
+
+def _alias_ctes(sql, pattern):
+    pp = parse_search_pattern(pattern)
+    m = search(sql, pp, 0)
+    while m.start != -1:
+        vv = m.variable_to_value
+        with_it = _CommaListIterator(vv.get('@@b'), WITH_COLUMNS)
+        sel_it = _CommaListIterator(vv.get('@@c'), SELECT)
+        repl = ''
+        while not with_it.done():
+            if sel_it.done():
+                break
+            expr = _s(sel_it.prefix) + ' as ' + with_it.full()
+            if repl:
+                repl += ','
+            repl += expr
+            with_it.next()
+            sel_it.next()
+        repl = sel_it.list_prefix + repl + sel_it.list_suffix
+        a = vv.get('@@a')
+        if a is None:
+            raise JavaError('NullPointerException')
+        body = pattern.replace('@@a', a).replace('(@@b)', '').replace('@@c', repl).replace('@@d', vv.get('@@d') or '')
+        sql = substring(sql, 0, m.start) + body + substring(sql, m.end)
+        m = search(sql, pp, m.start_token + 1)
+    return sql
+
+
+def _convert_select_list_references(sql, select_pattern, list_type):
+    pp = parse_search_pattern(select_pattern)
+    m = search(sql, pp, 0)
+    while m.start != -1:
+        vv = m.variable_to_value
+        select_list = vv.get('@@s')
+        repl = ''
+        it = _CommaListIterator(vv.get('@@r'), list_type)
+        while not it.done():
+            expr, suffix = it.prefix, it.suffix
+            expr_pp = parse_search_pattern(expr)
+            if it.is_single_column_reference():
+                repl += ', ' + expr + suffix
+            else:
+                sel_it = _CommaListIterator(select_list, SELECT)
+                found = False
+                i = 1
+                while not sel_it.done():
+                    if search(sel_it.prefix, expr_pp, 0).start != -1:
+                        found = True
+                        repl += ', ' + str(i) + suffix
+                        break
+                    i += 1
+                    sel_it.next()
+                if not found:
+                    repl += ', ' + expr + suffix
+            it.next()
+        repl = it.list_prefix + substring(repl, 1) + it.list_suffix
+        tail = substring(sql, m.end)
+        sql = substring(sql, 0, m.start)
+        for block in pp:
+            if sql:
+                sql += ' '
+            if block.is_variable:
+                sql += repl if block.text == '@@r' else _s(vv.get(block.text))
+            else:
+                sql += block.text
+        sql += tail
+        m = search(sql, pp, m.start_token + 1)
+    return sql
+
+
+def _lower_case(sql):
+    for t in tokenize_sql(sql):
+        if not t.in_quotes and not t.text.startswith('@'):
+            sql = substring(sql, 0, t.start) + t.text.lower() + substring(sql, t.end)
+    return sql
+
+
+def translate_bigquery(sql):
+    sql = _lower_case(sql)
+    sql = _alias_ctes(sql, 'with @@a (@@b) as (select @@c from @@d)')
+    sql = _alias_ctes(sql, 'with @@a (@@b) as (select @@c union @@d)')
+    sql = _alias_ctes(sql, 'with @@a (@@b) as (select @@c)')
+    sql = _alias_ctes(sql, ', @@a (@@b) as (select @@c from @@d)')
+    g = 'select @@s from @@b group by @@r'
+    for suffix in (';', ')', ' having', ' order by'):
+        sql = _convert_select_list_references(sql, g + suffix, GROUP_BY)
+    o = 'select @@s from @@b order by @@r'
+    for suffix in (';', ')'):
+        sql = _convert_select_list_references(sql, o + suffix, ORDER_BY)
+    return sql
+
+
+def _spark_create_table(sql):
+    if not sql.endswith(';'):
+        sql += ';'
+    pp = parse_search_pattern('CREATE TABLE @@table (@@definition)')
+    sql = re.sub(' +', ' ', trim(sql).replace('\t', ' '))
+    m = search(sql, pp, 0)
+    table = m.variable_to_value.get('@@table')
+    definition = m.variable_to_value.get('@@definition')
+    if table is not None and definition is not None:
+        table = table.replace('\r\n', '')
+        definition = definition.lower().replace('\r\n', '').replace(' as ', ' ')
+        cols = []
+        for f in split(definition, ','):
+            parts = split(trim(f), ' ')
+            if len(parts) < 2:
+                raise JavaError('ArrayIndexOutOfBoundsException')
+            cols.append('\tCAST(NULL AS ' + parts[1] + ') AS ' + parts[0])
+        sql = substring(sql, 0, m.start) + 'SELECT ' + ',\r\n'.join(cols) + ' INTO ' + table + ' WHERE 1 = 0'
+    return sql.replace(';', '')
+
+
+def translate_spark(sql):
+    parts = [_spark_create_table(p) for p in split_sql(sql)]
+    joined = trim(';\r\n'.join(parts))
+    if len(parts) > 1 or trim(sql).endswith(';'):
+        return joined + ';'
+    return joined