From b8d2b552cd23480cc7f042a60b00be2b95288eb9 Mon Sep 17 00:00:00 2001
From: Phillip Cloud <417981+cpcloud@users.noreply.github.com>
Date: Thu, 8 Feb 2024 08:04:57 -0500
Subject: [PATCH] refactor(docs): inline code and remove `gen_matrix.py`

---
 docs/.gitignore                      |  1 -
 docs/support_matrix.qmd              | 54 ++++++++++++++++++++++------
 gen_matrix.py                        | 45 -----------------------
 ibis/backends/flink/__init__.py      |  5 +++
 ibis/backends/flink/compiler/core.py |  3 ++
 5 files changed, 51 insertions(+), 57 deletions(-)
 delete mode 100644 gen_matrix.py

diff --git a/docs/.gitignore b/docs/.gitignore
index c6821696481f..3c9a23d5e780 100644
--- a/docs/.gitignore
+++ b/docs/.gitignore
@@ -14,7 +14,6 @@ diamonds.json
 *.ndjson
 reference/
 objects.json
-*support_matrix.csv
 
 # generated notebooks and files
 *.ipynb
diff --git a/docs/support_matrix.qmd b/docs/support_matrix.qmd
index d805ad99274d..48ec4d07bc4e 100644
--- a/docs/support_matrix.qmd
+++ b/docs/support_matrix.qmd
@@ -7,18 +7,49 @@ hide:
 
 ```{python}
 #| echo: false
-!python ../gen_matrix.py
-```
+from pathlib import Path
 
-```{python}
-#| echo: false
 import pandas as pd
 
-support_matrix = pd.read_csv("./backends/raw_support_matrix.csv")
-support_matrix = support_matrix.assign(
-    Category=support_matrix.Operation.map(lambda op: op.rsplit(".", 1)[0].rsplit(".", 1)[-1]),
-    Operation=support_matrix.Operation.map(lambda op: op.rsplit(".", 1)[-1]),
-).set_index(["Category", "Operation"])
+import ibis
+import ibis.expr.operations as ops
+
+
+def get_backends(exclude=()):
+    entry_points = sorted(ep.name for ep in ibis.util.backend_entry_points())
+    return [
+        (backend, getattr(ibis, backend))
+        for backend in entry_points
+        if backend not in exclude
+    ]
+
+
+def get_leaf_classes(op):
+    for child_class in op.__subclasses__():
+        if not child_class.__subclasses__():
+            yield child_class
+        else:
+            yield from get_leaf_classes(child_class)
+
+
+public_ops = frozenset(get_leaf_classes(ops.Value))
+support = {"Operation": [f"{op.__module__}.{op.__name__}" for op in public_ops]}
+support.update(
+    (name, list(map(backend.has_operation, public_ops)))
+    for name, backend in get_backends()
+)
+
+support_matrix = (
+    pd.DataFrame(support)
+    .assign(splits=lambda df: df.Operation.str.findall("[a-zA-Z_][a-zA-Z_0-9]*"))
+    .assign(
+        Category=lambda df: df.splits.str[-2],
+        Operation=lambda df: df.splits.str[-1],
+    )
+    .drop(["splits"], axis=1)
+    .set_index(["Category", "Operation"])
+    .sort_index()
+)
 all_visible_ops_count = len(support_matrix)
 coverage = pd.Index(
     support_matrix.sum()
@@ -70,15 +101,16 @@ dict(
 #| content: valuebox
 #| title: "Number of SQL backends"
 import importlib
-from ibis.backends.base.sql import BaseSQLBackend
+from ibis.backends.base.sqlglot import SQLGlotBackend
 
 sql_backends = sum(
     issubclass(
         importlib.import_module(f"ibis.backends.{entry_point.name}").Backend,
-        BaseSQLBackend
+        SQLGlotBackend
     )
     for entry_point in ibis.util.backend_entry_points()
 )
+assert sql_backends > 0
 dict(value=sql_backends, color="green", icon="database")
 ```
 
diff --git a/gen_matrix.py b/gen_matrix.py
deleted file mode 100644
index 9f9745cb7239..000000000000
--- a/gen_matrix.py
+++ /dev/null
@@ -1,45 +0,0 @@
-from __future__ import annotations
-
-from pathlib import Path
-
-import pandas as pd
-
-import ibis
-import ibis.expr.operations as ops
-
-
-def get_backends(exclude=()):
-    entry_points = sorted(ep.name for ep in ibis.util.backend_entry_points())
-    return [
-        (backend, getattr(ibis, backend))
-        for backend in entry_points
-        if backend not in exclude
-    ]
-
-
-def get_leaf_classes(op):
-    for child_class in op.__subclasses__():
-        if not child_class.__subclasses__():
-            yield child_class
-        else:
-            yield from get_leaf_classes(child_class)
-
-
-def main():
-    public_ops = frozenset(get_leaf_classes(ops.Value))
-    support = {"operation": [f"{op.__module__}.{op.__name__}" for op in public_ops]}
-    support.update(
-        (name, list(map(backend.has_operation, public_ops)))
-        for name, backend in get_backends()
-    )
-
-    df = pd.DataFrame(support).set_index("operation").sort_index()
-
-    with Path(ibis.__file__).parents[1].joinpath(
-        "docs", "backends", "raw_support_matrix.csv"
-    ).open(mode="w") as f:
-        df.to_csv(f, index_label="Operation")
-
-
-if __name__ == "__main__":
-    main()
diff --git a/ibis/backends/flink/__init__.py b/ibis/backends/flink/__init__.py
index 2ae904f505ba..679c7680de62 100644
--- a/ibis/backends/flink/__init__.py
+++ b/ibis/backends/flink/__init__.py
@@ -44,6 +44,11 @@ class Backend(BaseBackend, CanCreateDatabase, NoUrl):
     supports_temporary_tables = True
     supports_python_udfs = True
 
+    @property
+    def dialect(self):
+        # TODO: remove when ported to sqlglot
+        return self.compiler.dialect
+
     def do_connect(self, table_env: TableEnvironment) -> None:
         """Create a Flink `Backend` for use with Ibis.
 
diff --git a/ibis/backends/flink/compiler/core.py b/ibis/backends/flink/compiler/core.py
index f5d4c3774800..be187ebdb664 100644
--- a/ibis/backends/flink/compiler/core.py
+++ b/ibis/backends/flink/compiler/core.py
@@ -14,6 +14,7 @@
     TableSetFormatter,
 )
 from ibis.backends.base.sql.registry import quote_identifier
+from ibis.backends.base.sqlglot.dialects import Flink
 from ibis.backends.flink.translator import FlinkExprTranslator
 
 
@@ -96,6 +97,8 @@ class FlinkCompiler(Compiler):
 
     cheap_in_memory_tables = True
 
+    dialect = Flink
+
     @classmethod
     def to_sql(cls, node, context=None, params=None):
         if isinstance(node, ir.Expr):