File size: 10,711 Bytes
6bff5d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
"""SqlCompiler — IR → (SQL string, named-params dict).

Identifiers (table / column names) come from the catalog and are quoted
verbatim — they were verified by the IR validator against the catalog,
so injection through identifiers is not possible at this layer.
Values from filter clauses are ALWAYS parameterized.

The output `CompiledSql.sql` uses SQLAlchemy-style named placeholders
(`:p_0, :p_1, ...`) so it can be executed via `text(sql)` with a params
dict on a sync SQLAlchemy engine.

v1 supports the Postgres dialect only. Supabase reuses the same compiler
output (Supabase = Postgres). MySQL / BigQuery / Snowflake compilers will
be separate classes that implement `BaseCompiler`.
"""

from __future__ import annotations

from dataclasses import dataclass, field
from typing import Any

from ...catalog.models import Catalog, Column, Source, Table
from ..ir.models import (
    AggSelect,
    ColumnSelect,
    FilterClause,
    OrderByClause,
    QueryIR,
    SelectItem,
)
from .base import BaseCompiler


@dataclass
class CompiledSql:
    sql: str
    params: dict[str, Any] = field(default_factory=dict)


class SqlCompilerError(Exception):
    pass


_NULLARY_OPS = frozenset({"is_null", "is_not_null"})
_LIST_OPS = frozenset({"in", "not_in"})
_COMPARISON_OPS = frozenset({"=", "!=", "<", "<=", ">", ">="})


class SqlCompiler(BaseCompiler):
    """Deterministic IR → Postgres SQL. No LLM."""

    def __init__(self, catalog: Catalog, dialect: str = "postgres") -> None:
        if dialect not in {"postgres", "supabase"}:
            raise SqlCompilerError(
                f"only 'postgres' / 'supabase' supported in v1, got {dialect!r}"
            )
        self._catalog = catalog
        self._dialect = dialect

    def compile(self, ir: QueryIR) -> CompiledSql:
        _, table, cols_by_id = self._lookup(ir)
        params: dict[str, Any] = {}
        param_seq = [0]

        select_clause, select_aliases = self._build_select(ir.select, table, cols_by_id)
        from_clause = self._build_from(table)
        where_clause = self._build_where(ir.filters, table, cols_by_id, params, param_seq)
        groupby_clause = self._build_groupby(ir.group_by, table, cols_by_id)
        orderby_clause = self._build_orderby(
            ir.order_by, table, cols_by_id, select_aliases
        )
        limit_clause = self._build_limit(ir.limit)

        parts: list[str] = [select_clause, from_clause]
        for clause in (where_clause, groupby_clause, orderby_clause, limit_clause):
            if clause:
                parts.append(clause)

        return CompiledSql(sql=" ".join(parts), params=params)

    # ------------------------------------------------------------------
    # Catalog lookup
    # ------------------------------------------------------------------

    def _lookup(self, ir: QueryIR) -> tuple[Source, Table, dict[str, Column]]:
        source = next(
            (s for s in self._catalog.sources if s.source_id == ir.source_id), None
        )
        if source is None:
            raise SqlCompilerError(f"source_id {ir.source_id!r} not in catalog")
        table = next(
            (t for t in source.tables if t.table_id == ir.table_id), None
        )
        if table is None:
            raise SqlCompilerError(
                f"table_id {ir.table_id!r} not in source {ir.source_id!r}"
            )
        return source, table, {c.column_id: c for c in table.columns}

    # ------------------------------------------------------------------
    # Identifier quoting
    # ------------------------------------------------------------------

    @staticmethod
    def _qident(name: str) -> str:
        """Postgres-style double-quoted identifier with embedded-quote escape."""
        return '"' + name.replace('"', '""') + '"'

    def _qcol(self, table: Table, col: Column) -> str:
        return f"{self._qident(table.name)}.{self._qident(col.name)}"

    # ------------------------------------------------------------------
    # Clauses
    # ------------------------------------------------------------------

    def _build_select(
        self,
        items: list[SelectItem],
        table: Table,
        cols_by_id: dict[str, Column],
    ) -> tuple[str, set[str]]:
        if not items:
            raise SqlCompilerError("select clause cannot be empty")
        parts: list[str] = []
        aliases: set[str] = set()
        for i, item in enumerate(items):
            expr, alias = self._select_item(item, table, cols_by_id, i)
            if alias:
                parts.append(f"{expr} AS {self._qident(alias)}")
                aliases.add(alias)
            else:
                parts.append(expr)
        return "SELECT " + ", ".join(parts), aliases

    def _select_item(
        self,
        item: SelectItem,
        table: Table,
        cols_by_id: dict[str, Column],
        index: int,
    ) -> tuple[str, str | None]:
        if isinstance(item, ColumnSelect):
            col = self._require_col(cols_by_id, item.column_id, f"select[{index}]")
            return self._qcol(table, col), item.alias
        if not isinstance(item, AggSelect):
            raise SqlCompilerError(
                f"select[{index}]: unknown SelectItem kind {type(item).__name__}"
            )
        return self._compile_agg(item, table, cols_by_id, index), item.alias

    def _compile_agg(
        self,
        item: AggSelect,
        table: Table,
        cols_by_id: dict[str, Column],
        index: int,
    ) -> str:
        if item.fn == "count_distinct":
            if item.column_id is None:
                raise SqlCompilerError(
                    f"select[{index}].fn=count_distinct requires column_id"
                )
            col = self._require_col(cols_by_id, item.column_id, f"select[{index}]")
            return f"COUNT(DISTINCT {self._qcol(table, col)})"
        if item.column_id is None:
            if item.fn != "count":
                raise SqlCompilerError(
                    f"select[{index}].fn={item.fn!r} requires column_id "
                    "(only 'count' may omit it for COUNT(*))"
                )
            return "COUNT(*)"
        col = self._require_col(cols_by_id, item.column_id, f"select[{index}]")
        return f"{item.fn.upper()}({self._qcol(table, col)})"

    def _build_from(self, table: Table) -> str:
        return f"FROM {self._qident(table.name)}"

    def _build_where(
        self,
        filters: list[FilterClause],
        table: Table,
        cols_by_id: dict[str, Column],
        params: dict[str, Any],
        param_seq: list[int],
    ) -> str:
        if not filters:
            return ""
        parts = [
            self._compile_filter(f, table, cols_by_id, params, param_seq, index=i)
            for i, f in enumerate(filters)
        ]
        return "WHERE " + " AND ".join(parts)

    def _compile_filter(
        self,
        f: FilterClause,
        table: Table,
        cols_by_id: dict[str, Column],
        params: dict[str, Any],
        param_seq: list[int],
        index: int,
    ) -> str:
        col = self._require_col(cols_by_id, f.column_id, f"filters[{index}]")
        col_ref = self._qcol(table, col)
        op = f.op

        if op == "is_null":
            return f"{col_ref} IS NULL"
        if op == "is_not_null":
            return f"{col_ref} IS NOT NULL"

        if op in _LIST_OPS:
            if not isinstance(f.value, list) or not f.value:
                raise SqlCompilerError(
                    f"filters[{index}]: op {op!r} requires a non-empty list value"
                )
            placeholders = [
                ":" + self._next_param(params, param_seq, v) for v in f.value
            ]
            sql_op = "IN" if op == "in" else "NOT IN"
            return f"{col_ref} {sql_op} ({', '.join(placeholders)})"

        if op == "between":
            if not isinstance(f.value, list) or len(f.value) != 2:
                raise SqlCompilerError(
                    f"filters[{index}]: op 'between' requires a list of two values"
                )
            lo = self._next_param(params, param_seq, f.value[0])
            hi = self._next_param(params, param_seq, f.value[1])
            return f"{col_ref} BETWEEN :{lo} AND :{hi}"

        if op == "like":
            p = self._next_param(params, param_seq, f.value)
            return f"{col_ref} LIKE :{p}"

        if op in _COMPARISON_OPS:
            p = self._next_param(params, param_seq, f.value)
            return f"{col_ref} {op} :{p}"

        # Should not reach here — IRValidator already filters disallowed ops
        raise SqlCompilerError(f"filters[{index}]: unhandled op {op!r}")

    def _build_groupby(
        self,
        group_by: list[str],
        table: Table,
        cols_by_id: dict[str, Column],
    ) -> str:
        if not group_by:
            return ""
        parts = [
            self._qcol(table, self._require_col(cols_by_id, col_id, f"group_by[{i}]"))
            for i, col_id in enumerate(group_by)
        ]
        return "GROUP BY " + ", ".join(parts)

    def _build_orderby(
        self,
        order_by: list[OrderByClause],
        table: Table,
        cols_by_id: dict[str, Column],
        select_aliases: set[str],
    ) -> str:
        if not order_by:
            return ""
        parts: list[str] = []
        for i, ob in enumerate(order_by):
            if ob.column_id in cols_by_id:
                ref = self._qcol(table, cols_by_id[ob.column_id])
            elif ob.column_id in select_aliases:
                ref = self._qident(ob.column_id)
            else:
                raise SqlCompilerError(
                    f"order_by[{i}].column_id: {ob.column_id!r} not in table "
                    "columns or select aliases"
                )
            parts.append(f"{ref} {ob.dir.upper()}")
        return "ORDER BY " + ", ".join(parts)

    def _build_limit(self, limit: int | None) -> str:
        if limit is None:
            return ""
        return f"LIMIT {int(limit)}"

    # ------------------------------------------------------------------
    # Helpers
    # ------------------------------------------------------------------

    @staticmethod
    def _next_param(
        params: dict[str, Any], param_seq: list[int], value: Any
    ) -> str:
        name = f"p_{param_seq[0]}"
        param_seq[0] += 1
        params[name] = value
        return name

    @staticmethod
    def _require_col(
        cols_by_id: dict[str, Column], col_id: str, where: str
    ) -> Column:
        col = cols_by_id.get(col_id)
        if col is None:
            raise SqlCompilerError(f"{where}.column_id: {col_id!r} not in table")
        return col