execsql2 2.22.5__py3-none-any.whl → 2.22.7__py3-none-any.whl

execsql/format.py

@@ -278,6 +278,64 @@ def _sql_literal_texts(sql: str) -> list[str]:
     return [sql[start:end] for start, end, _ in _iter_sql_literals(sql)]
 
 
+def _literal_line_starts(lines: list[str]) -> list[int]:
+    """Return the character offset at which each of *lines* starts once joined."""
+    starts: list[int] = []
+    offset = 0
+    for line in lines:
+        starts.append(offset)
+        offset += len(line) + 1  # +1 for the newline joined between lines
+    return starts
+
+
+def _literal_interior_lines(lines: list[str]) -> set[int]:
+    """Return indices of *lines* that begin inside a multi-line string literal.
+
+    The line that *opens* a literal is ordinary SQL up to the delimiter, so it
+    is indented with the statement as usual.  Every later line of that literal
+    — through and including the one holding the closing delimiter — begins
+    inside the string, which makes its leading whitespace part of the stored
+    value rather than layout.  Re-indenting those lines changes what the
+    database receives, so callers must emit them verbatim.
+
+    This covers every literal kind the scanner reports, not just dollar-quoted
+    bodies: an ordinary ``'…'`` string spanning lines carries its newlines and
+    indentation exactly the same way.
+    """
+    if len(lines) < 2:
+        return set()
+    text = "\n".join(lines)
+    starts = _literal_line_starts(lines)
+
+    interior: set[int] = set()
+    for start, end, _kind in _iter_sql_literals(text):
+        interior.update(i for i, line_start in enumerate(starts) if start < line_start < end)
+    return interior
+
+
+def _literal_spanning_lines(lines: list[str]) -> set[int]:
+    """Return indices of every line that any multi-line literal touches.
+
+    Unlike :func:`_literal_interior_lines` this also includes the line that
+    *opens* the literal.  Passes that move text between lines — rather than
+    only adjusting leading whitespace — must leave the whole span alone, since
+    the opening line holds literal content after its delimiter.
+    """
+    if len(lines) < 2:
+        return set()
+    text = "\n".join(lines)
+    starts = _literal_line_starts(lines)
+
+    spanning: set[int] = set()
+    for start, end, _kind in _iter_sql_literals(text):
+        touched = [i for i, line_start in enumerate(starts) if start < line_start < end]
+        if not touched:
+            continue  # single-line literal — nothing spans
+        spanning.update(touched)
+        spanning.add(min(touched) - 1)  # the line that opens the literal
+    return spanning
+
+
 # Placeholder standing in for a masked E'...' literal.  It is a plain literal
 # so that sqlglot sees a string where a string was, and lays the statement out
 # the same way it would have for the real one.
@@ -398,7 +456,21 @@ def _sqlglot_format(
 
     try:
         with contextlib.redirect_stderr(io.StringIO()):
-            ast = sqlglot.parse(protected, read="postgres", error_level=sqlglot_errors.ErrorLevel.IGNORE)
+            # Parse with RAISE, not IGNORE.  Under IGNORE sqlglot answers a
+            # statement it cannot parse with a *partial* AST — the tokens it
+            # failed on are simply absent — and regenerating from that AST
+            # writes back SQL that no longer means what the author wrote.
+            # ``INSERT ... CROSS JOIN LATERAL (VALUES ...) AS g(a, b) ON
+            # CONFLICT (a) DO NOTHING`` came back with ``DO NOTHING`` deleted:
+            # still one statement, still 88% of the input's alphanumeric
+            # characters, no string literals to compare, so every guard below
+            # passed it through.  The guards are quantitative and this loss is
+            # qualitative — a dropped ``DISTINCT``, ``CASCADE``, ``DESC`` or
+            # ``NOT`` is smaller still, and no threshold separates those from
+            # ordinary reformatting.  Only the parser knows whether it
+            # understood the whole statement, so ask it: input that does not
+            # parse is left exactly as written.
+            ast = sqlglot.parse(protected, read="postgres", error_level=sqlglot_errors.ErrorLevel.RAISE)
             statements: list[str] = []
             for node in ast:
                 if node is None:
@@ -466,6 +538,10 @@ def _sqlglot_format(
         if restored is None:
             return sql_lines
         return _restore_variables(restored, replacements).split("\n")
+    except sqlglot_errors.ParseError:
+        # Unparsable input: anything generated from a partial parse is
+        # untrustworthy, so emit the original lines untouched.
+        return sql_lines
     except Exception:
         return sql_lines
 
@@ -503,6 +579,14 @@ def _has_mid_statement_comments(lines: list[str]) -> bool:
 
 _CMT_MARKER = "EXECSQL_CMTMARKER_"
 _CMT_MARKER_RE = re.compile(rf"/\*\s*({re.escape(_CMT_MARKER)}\d+)\s*\*/")
+# A whole run of adjacent markers plus the whitespace injected around them.
+# Markers are written as ``/* marker */ line`` and several consecutive source
+# comments attach several markers to one line, so removing them one at a time
+# leaves a separator space behind for each.  When sqlglot moves the run into
+# the middle of an expression that residue shows up as ``AND   RTRIM(`` and is
+# only normalised on the following pass, which costs an extra pass to
+# converge.  Matching the run as a unit removes it cleanly.  See issue #35.
+_CMT_MARKER_RUN_RE = re.compile(rf"\s*(?:/\*\s*{re.escape(_CMT_MARKER)}\d+\s*\*/\s*)+")
 
 
 def _format_preserving_comments(
@@ -570,12 +654,16 @@ def _format_preserving_comments(
         markers_here = _CMT_MARKER_RE.findall(fline)
         if markers_here:
             # Strip markers to get the underlying SQL line and its indent
-            cleaned = _CMT_MARKER_RE.sub("", fline).strip()
-            # Determine indent: use the SQL line's indent from sqlglot
-            line_indent = ""
-            if cleaned:
-                raw_cleaned = _CMT_MARKER_RE.sub("", fline)
-                line_indent = raw_cleaned[: len(raw_cleaned) - len(raw_cleaned.lstrip())]
+            cleaned = _CMT_MARKER_RUN_RE.sub(" ", fline).strip()
+            # Indent comes from the line's own leading whitespace, never from
+            # what is left after removing the marker.  Markers are injected as
+            # ``/* marker */ line`` — with a separating space — so measuring
+            # after removal counts that space as indentation.  Whenever
+            # sqlglot leaves the line untouched (an unparsable statement falls
+            # back verbatim) the extra space is re-measured and re-added on the
+            # next run, growing the indent by one on every pass and never
+            # converging.  See issue #35.
+            line_indent = fline[: len(fline) - len(fline.lstrip())]
             for m in markers_here:
                 if m in comment_store:
                     orig = comment_store[m]
@@ -671,12 +759,24 @@ def format_sql_block(
     if not non_empty:
         return [""] * len(lines)
 
-    base = min(len(line) - len(line.lstrip()) for line in non_empty)
+    # Lines that begin inside a multi-line literal carry content, not layout —
+    # dedenting or indenting them changes the value the database stores.
+    # Exclude them from the indent arithmetic and emit them verbatim.
+    interior = _literal_interior_lines(lines)
+    if interior:
+        # format_file already withholds dollar-quoted blocks from sqlglot; keep
+        # that true here so the line indices below stay aligned with the output.
+        use_sql = False
+
+    layout_lines = [line for i, line in enumerate(lines) if line.strip() and i not in interior]
+    base = min((len(line) - len(line.lstrip()) for line in layout_lines), default=0)
     target_prefix = " " * (depth * indent)
-    rebased = [line[base:] if line.strip() else "" for line in lines]
+    rebased = [line if i in interior else (line[base:] if line.strip() else "") for i, line in enumerate(lines)]
 
     if not use_sql:
-        return [target_prefix + line if line.strip() else "" for line in rebased]
+        return [
+            line if i in interior else (target_prefix + line if line.strip() else "") for i, line in enumerate(rebased)
+        ]
 
     # When comments appear mid-statement, use the marker-based approach
     # which preserves both comments AND sqlglot formatting.  When all
@@ -747,6 +847,9 @@ def _normalize_to_trailing_comma(text: str) -> str:
     every invocation. Comments between the two SQL lines stay in place.
     """
     lines = text.split("\n")
+    # Symmetric with _apply_leading_comma: a leading comma inside a multi-line
+    # literal is data, not layout, so the whole span is left alone.
+    protected = _literal_spanning_lines(lines)
 
     def find_prev_sql_line(idx: int) -> int:
         k = idx - 1
@@ -756,7 +859,7 @@ def _normalize_to_trailing_comma(text: str) -> str:
 
     for i, line in enumerate(lines):
         stripped = line.lstrip()
-        if not stripped.startswith(",") or _is_comment_only(line):
+        if not stripped.startswith(",") or _is_comment_only(line) or i in protected:
             continue
         # Don't try to rewrite leading-comma inside a comment-only line.
         # Move the comma onto the previous SQL line as a trailing `,`.
@@ -792,15 +895,19 @@ def _apply_leading_comma(text: str) -> str:
     TestIdempotency).
     """
     lines = text.split("\n")
+    # A comma inside a multi-line string literal is data. Moving it to the next
+    # line would rewrite the stored value, so leave every line such a literal
+    # touches — including the one that opens it — exactly as it is.
+    protected = _literal_spanning_lines(lines)
     i = 0
     n = len(lines)
     while i < n:
         rstripped = lines[i].rstrip()
-        if rstripped.endswith(",") and not _is_comment_only(lines[i]):
+        if rstripped.endswith(",") and not _is_comment_only(lines[i]) and i not in protected:
             j = i + 1
             while j < n and (not lines[j].strip() or _is_comment_only(lines[j])):
                 j += 1
-            if j < n:
+            if j < n and j not in protected:
                 stripped = lines[i].rstrip()
                 comma_idx = stripped.rfind(",")
                 lines[i] = stripped[:comma_idx] + stripped[comma_idx + 1 :]

{execsql2-2.22.5.dist-info → execsql2-2.22.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: execsql2
-Version: 2.22.5
+Version: 2.22.7
 Summary: Runs a SQL script against a PostgreSQL, SQLite, MariaDB/MySQL, DuckDB, Firebird, MS-Access, MS-SQL-Server, or Oracle database, or an ODBC DSN. Provides metacommands to import and export data, copy data between databases, conditionally execute SQL and metacommands, and dynamically alter SQL and metacommands with substitution variables.
 Project-URL: Homepage, https://execsql2.readthedocs.io
 Project-URL: Repository, https://github.com/geocoug/execsql
@@ -384,7 +384,7 @@ execsql-format --no-sql --in-place scripts/
 ```yaml
 repos:
   - repo: https://github.com/geocoug/execsql
-    rev: v2.22.5
+    rev: v2.22.7
     hooks:
       - id: execsql-format
 ```

{execsql2-2.22.5.dist-info → execsql2-2.22.7.dist-info}/RECORD

@@ -3,7 +3,7 @@ execsql/__main__.py,sha256=HdbK-SAhyUmfB6xINY5AzxdMSxGzWSGEG_2dv42Jn64,315
 execsql/api.py,sha256=EOtBwMnm-8fmB_KmvxyjglR6C7CjdYhCPBisJ9CFfJg,22227
 execsql/config.py,sha256=txKziUJLV7UPonj2sGFgkmlinDdSV50aHmR_cuCbEIo,34369
 execsql/exceptions.py,sha256=GlphAiR8iZu4UR4U50WgSqEUMd9_8AeQJ_hhPcJOeQU,9381
-execsql/format.py,sha256=tfg0m3EbDVRlAR3ZhwV8BjgMFckL3u3IdldyCONrutU,41400
+execsql/format.py,sha256=oJvAxDaWi-TQAnj_enwuEH-wtjZylKf67QWwHrSNEUU,47254
 execsql/models.py,sha256=-DWTVrPNwM-n1h3e3rXMoBv9-wpWVdZahyy4RB7fRRE,15502
 execsql/parser.py,sha256=aOxZ7Mzgvk7G4-nvy9Bgz7xlaZm6oo81cffDeBk_LCk,15597
 execsql/plugins.py,sha256=l82VWa5NpvOQWD6vcO-WKP-vtn0wp9__wWDFAbwxZg0,12838
@@ -101,23 +101,23 @@ execsql/utils/numeric.py,sha256=_7bi5R6pHjMCkOPne_Sh5nUj-B8e9g6WFmjptFHaunA,1573
 execsql/utils/regex.py,sha256=B3mSBhRRx_DpUnX_t9IoYd05KvWAebiLMCZqQAmEwcw,3885
 execsql/utils/strings.py,sha256=UQNjpRCEFa1UO6feU-M-9e24wWAvizs_iu_4fFusLxo,8516
 execsql/utils/timer.py,sha256=eDYf5VzCNFk7oo90InJucUm3XcBdhYMogjZMqeg9xzc,1899
-execsql2-2.22.5.data/data/execsql2_extras/README.md,sha256=vX4NTL095dUoA_hesyRMGYBorEZ_Y_tJ9qrd-MVV09I,5032
-execsql2-2.22.5.data/data/execsql2_extras/config_settings.sqlite,sha256=aY5cxR7Q7J6zJ4bC9lu5mHUrhy211Cq3MNKPQVCt02E,20480
-execsql2-2.22.5.data/data/execsql2_extras/example_config_prompt.sql,sha256=2e8KzzVWhho8KxYVHETSVmZdhW7wodioDsqBLSL6m4s,7487
-execsql2-2.22.5.data/data/execsql2_extras/make_config_db.sql,sha256=WwyC6dK-Eh5CAVppiBCDHqiI1_wEI9U95Ytpr4lsZkg,8726
-execsql2-2.22.5.data/data/execsql2_extras/md_compare.sql,sha256=qYYVAjSeHZzjszxV3Bv6bg8Ckbq2kMHl87_gh4sywMU,24140
-execsql2-2.22.5.data/data/execsql2_extras/md_glossary.sql,sha256=hkZ2Onn57LAKKsuXxzhR8tPtcWXkmWEQkwPE58-Tm2k,10796
-execsql2-2.22.5.data/data/execsql2_extras/md_upsert.sql,sha256=_CAK4BzEboRXTNy03SJR-oOjcEdSNMuRBPL6noWUptY,112560
-execsql2-2.22.5.data/data/execsql2_extras/pg_compare.sql,sha256=1zJd4hVUKHR0tncc2qTBC9B4qVV4Us2ITkJpsjN3tMw,24352
-execsql2-2.22.5.data/data/execsql2_extras/pg_glossary.sql,sha256=IKuwna-_8b20ljSkXZruuiQigrCpo7ueQdUqd1MXiuI,9908
-execsql2-2.22.5.data/data/execsql2_extras/pg_upsert.sql,sha256=HpPJtTHvpEjQy03j-3iPxDEOHMRkudOg7O4D4YR38UI,108315
-execsql2-2.22.5.data/data/execsql2_extras/script_template.sql,sha256=2J35ddZPguJ-vwTsz83wErv0jiWUyJcdW_JM0mNKDXA,11155
-execsql2-2.22.5.data/data/execsql2_extras/ss_compare.sql,sha256=j1qVNUPXQsEU7-DoVgDJCGcE0EuIl7whLBT3fgeiMAo,24833
-execsql2-2.22.5.data/data/execsql2_extras/ss_glossary.sql,sha256=2gLxv34xzKt0vy7hSzJH7a9JiMC3ETrv9MofxQwAibU,13065
-execsql2-2.22.5.data/data/execsql2_extras/ss_upsert.sql,sha256=G_8rQ0VzuKIZHWs24O_WrfzpC5S27R1JsL-bFBR3SUQ,117730
-execsql2-2.22.5.dist-info/METADATA,sha256=OHGAN6pqfqOTBPDSst372rskkKNgeXUofH9K_mfl3sc,20382
-execsql2-2.22.5.dist-info/WHEEL,sha256=zOwg4jB6zX2kU910N-cMawjivD6tO8NEWvE12je1bVk,87
-execsql2-2.22.5.dist-info/entry_points.txt,sha256=sUOxkM-dN1eBGGpSpDLsAaE0yNXYQKWZAfxPOlMkQyk,90
-execsql2-2.22.5.dist-info/licenses/LICENSE.txt,sha256=LBdhuxejF8_bLCHZ2kWfmDXpDGUu914Gbd6_3JjCRe0,676
-execsql2-2.22.5.dist-info/licenses/NOTICE,sha256=McYzgxYav3U1OaVsY4Su1sfBrfmplpRdA9b6-gCDQCg,342
-execsql2-2.22.5.dist-info/RECORD,,
+execsql2-2.22.7.data/data/execsql2_extras/README.md,sha256=vX4NTL095dUoA_hesyRMGYBorEZ_Y_tJ9qrd-MVV09I,5032
+execsql2-2.22.7.data/data/execsql2_extras/config_settings.sqlite,sha256=aY5cxR7Q7J6zJ4bC9lu5mHUrhy211Cq3MNKPQVCt02E,20480
+execsql2-2.22.7.data/data/execsql2_extras/example_config_prompt.sql,sha256=2e8KzzVWhho8KxYVHETSVmZdhW7wodioDsqBLSL6m4s,7487
+execsql2-2.22.7.data/data/execsql2_extras/make_config_db.sql,sha256=WwyC6dK-Eh5CAVppiBCDHqiI1_wEI9U95Ytpr4lsZkg,8726
+execsql2-2.22.7.data/data/execsql2_extras/md_compare.sql,sha256=qYYVAjSeHZzjszxV3Bv6bg8Ckbq2kMHl87_gh4sywMU,24140
+execsql2-2.22.7.data/data/execsql2_extras/md_glossary.sql,sha256=hkZ2Onn57LAKKsuXxzhR8tPtcWXkmWEQkwPE58-Tm2k,10796
+execsql2-2.22.7.data/data/execsql2_extras/md_upsert.sql,sha256=_CAK4BzEboRXTNy03SJR-oOjcEdSNMuRBPL6noWUptY,112560
+execsql2-2.22.7.data/data/execsql2_extras/pg_compare.sql,sha256=1zJd4hVUKHR0tncc2qTBC9B4qVV4Us2ITkJpsjN3tMw,24352
+execsql2-2.22.7.data/data/execsql2_extras/pg_glossary.sql,sha256=IKuwna-_8b20ljSkXZruuiQigrCpo7ueQdUqd1MXiuI,9908
+execsql2-2.22.7.data/data/execsql2_extras/pg_upsert.sql,sha256=HpPJtTHvpEjQy03j-3iPxDEOHMRkudOg7O4D4YR38UI,108315
+execsql2-2.22.7.data/data/execsql2_extras/script_template.sql,sha256=2J35ddZPguJ-vwTsz83wErv0jiWUyJcdW_JM0mNKDXA,11155
+execsql2-2.22.7.data/data/execsql2_extras/ss_compare.sql,sha256=j1qVNUPXQsEU7-DoVgDJCGcE0EuIl7whLBT3fgeiMAo,24833
+execsql2-2.22.7.data/data/execsql2_extras/ss_glossary.sql,sha256=2gLxv34xzKt0vy7hSzJH7a9JiMC3ETrv9MofxQwAibU,13065
+execsql2-2.22.7.data/data/execsql2_extras/ss_upsert.sql,sha256=G_8rQ0VzuKIZHWs24O_WrfzpC5S27R1JsL-bFBR3SUQ,117730
+execsql2-2.22.7.dist-info/METADATA,sha256=DbIBWCsTnJIRQx1h0UKA9kB5kXFMybxn7U9j-xWG8P4,20382
+execsql2-2.22.7.dist-info/WHEEL,sha256=zOwg4jB6zX2kU910N-cMawjivD6tO8NEWvE12je1bVk,87
+execsql2-2.22.7.dist-info/entry_points.txt,sha256=sUOxkM-dN1eBGGpSpDLsAaE0yNXYQKWZAfxPOlMkQyk,90
+execsql2-2.22.7.dist-info/licenses/LICENSE.txt,sha256=LBdhuxejF8_bLCHZ2kWfmDXpDGUu914Gbd6_3JjCRe0,676
+execsql2-2.22.7.dist-info/licenses/NOTICE,sha256=McYzgxYav3U1OaVsY4Su1sfBrfmplpRdA9b6-gCDQCg,342
+execsql2-2.22.7.dist-info/RECORD,,