Text2Gremlin Data Generation and Model Fine-Tuning System (Vertical Scenarios and General Scenarios)

.licenserc.yaml

@@ -82,6 +82,9 @@ header: # `header` section is configurations for source codes license header.
     - '**/poetry.lock'
     - '.github/**/*'
     - 'docker/**/*'
+    - '**/*.interp'
+    - '**/*.tokens'
+    - '**/*.csv'
 
   comment: on-failure
   # on what condition license-eye will comment on the pull request, `on-failure`, `always`, `never`.

pyproject.toml

@@ -162,6 +162,9 @@ addopts = "--strict-markers --strict-config"
 [tool.ruff]
 line-length = 120
 target-version = "py310"
+extend-exclude = [
+    "text2gremlin/AST_Text2Gremlin/base/gremlin/*.py",
+]
 
 [tool.ruff.lint]
 # Select a broad set of rules for comprehensive checks.
@@ -187,6 +190,18 @@ ignore = [
 "tests/**/*.py" = ["T20"]
 "hugegraph-ml/src/hugegraph_ml/examples/**/*.py" = ["T20"]
 "hugegraph-python-client/src/pyhugegraph/structure/*.py" = ["N802"]
+"text2gremlin/**/*.py" = [
+    "E501",   # Long Chinese prompts and generated Gremlin visitor fragments are kept readable.
+    "E741",   # Gremlin examples use compact variable names in local comprehensions.
+    "F403",   # ANTLR visitor code relies on antlr4's compatibility import style.
+    "F811",   # Visitor methods mirror grammar alternatives and may intentionally repeat names.
+    "N999",   # Keep existing module names used by standalone scripts.
+    "RUF002", # Chinese docstrings intentionally use full-width punctuation.
+    "RUF012", # Class-level step configuration dictionaries are constants in practice.
+    "SIM102", # Keep complex traversal-generation branching explicit.
+    "SIM108", # Keep complex traversal-generation branching explicit.
+    "T20",    # Standalone CLI/data-generation scripts write progress to stdout.
+]
 
 [tool.ruff.lint.isort]
 known-first-party = ["hugegraph_llm", "hugegraph_python_client", "hugegraph_ml", "vermeer_python_client"]

text2gremlin/AST_Text2Gremlin/.gitignore

@@ -0,0 +1,13 @@
+# 配置文件
+config.json
+.env
+output/
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+*.egg-info/
+.eggs/