Merging upstream version 26.26.0.

Signed-off-by: Daniel Baumann <daniel@debian.org>

.github/scripts/format_benchmark.py

@@ -0,0 +1,81 @@
+#!/usr/bin/env python3
+"""Format benchmark comparison output with visual indicators for GitHub markdown."""
+
+import re
+import sys
+
+
+def format_benchmark_output(content):
+    """Add visual formatting to benchmark comparison output."""
+    lines = content.split("\n")
+    formatted_lines = []
+
+    for line in lines:
+        # Skip empty lines and headers
+        if not line.strip() or line.startswith("|") and "---" in line:
+            formatted_lines.append(line)
+            continue
+
+        # Process benchmark result lines
+        if "|" in line and ("faster" in line or "slower" in line):
+            # Extract the speed factor (e.g., "1.23x faster" or "1.10x slower")
+            speed_match = re.search(r"(\d+\.\d+)x\s+(faster|slower)", line)
+            if speed_match:
+                factor = float(speed_match.group(1))
+                direction = speed_match.group(2)
+
+                # Add visual indicators based on performance
+                if direction == "faster":
+                    # Green indicator for faster
+                    if factor >= 2.0:
+                        indicator = "🟢🟢"  # Double green for 2x+ faster
+                    elif factor >= 1.1:
+                        indicator = "🟢"  # Single green for 1.1x+ faster
+                    else:
+                        indicator = "⚪"  # White for marginal improvement
+                    formatted_text = f"{indicator} **{speed_match.group(0)}**"
+                else:
+                    # Red indicator for slower
+                    if factor >= 2.0:
+                        indicator = "🔴🔴"  # Double red for 2x+ slower
+                    elif factor >= 1.1:
+                        indicator = "🔴"  # Single red for 1.1x+ slower
+                    else:
+                        indicator = "⚪"  # White for marginal slowdown
+                    formatted_text = f"{indicator} **{speed_match.group(0)}**"
+
+                # Replace the original text with formatted version
+                line = line.replace(speed_match.group(0), formatted_text)
+            elif "not significant" in line:
+                # Add neutral indicator for non-significant changes
+                line = re.sub(r"not significant", "⚪ not significant", line)
+
+        formatted_lines.append(line)
+
+    return "\n".join(formatted_lines)
+
+
+def main():
+    if len(sys.argv) != 2:
+        print("Usage: python format_benchmark.py <input_file>")
+        sys.exit(1)
+
+    input_file = sys.argv[1]
+
+    try:
+        with open(input_file, "r") as f:
+            content = f.read()
+
+        formatted = format_benchmark_output(content)
+        print(formatted)
+
+    except FileNotFoundError:
+        print(f"Error: File '{input_file}' not found")
+        sys.exit(1)
+    except Exception as e:
+        print(f"Error: {e}")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/benchmark-sqlglot.yml

@@ -61,14 +61,27 @@ jobs:
       - name: Compare benchmarks and save results
         run: |
           source ./.venv/bin/activate
-          python -m pyperf compare_to bench_parse_pr.json bench_parse_main.json --table --table-format=md > bench_parse_comparison.txt
+          python -m pyperf compare_to bench_parse_main.json bench_parse_pr.json --table --table-format=md > bench_parse_comparison_raw.txt
-          python -m pyperf compare_to bench_optimize_pr.json bench_optimize_main.json --table --table-format=md > bench_optimize_comparison.txt
+          python -m pyperf compare_to bench_optimize_main.json bench_optimize_pr.json --table --table-format=md > bench_optimize_comparison_raw.txt
+
+          # Format with colors
+          python .github/scripts/format_benchmark.py bench_parse_comparison_raw.txt > bench_parse_comparison.txt
+          python .github/scripts/format_benchmark.py bench_optimize_comparison_raw.txt > bench_optimize_comparison.txt
       - name: Combine benchmark outputs
         run: |
-          echo "## Parsing Benchmark" > combined_benchmarks.md
+          echo "## Benchmark Results" > combined_benchmarks.md
+          echo "" >> combined_benchmarks.md
+          echo "**Legend:**" >> combined_benchmarks.md
+          echo "- 🟢🟢 = 2x+ faster" >> combined_benchmarks.md
+          echo "- 🟢 = 1.1x - 2x faster" >> combined_benchmarks.md
+          echo "- ⚪ = No significant change (< 1.1x)" >> combined_benchmarks.md
+          echo "- 🔴 = 1.1x - 2x slower" >> combined_benchmarks.md
+          echo "- 🔴🔴 = 2x+ slower" >> combined_benchmarks.md
+          echo "" >> combined_benchmarks.md
+          echo "### Parsing Benchmark" >> combined_benchmarks.md
           cat bench_parse_comparison.txt >> combined_benchmarks.md
           echo -e "\n---\n" >> combined_benchmarks.md
-          echo "## Optimization Benchmark" >> combined_benchmarks.md
+          echo "### Optimization Benchmark" >> combined_benchmarks.md
           cat bench_optimize_comparison.txt >> combined_benchmarks.md
       - name: Comment on PR for parse benchmark results
         uses: peter-evans/create-or-update-comment@v4

CHANGELOG.md

@@ -1,6 +1,11 @@
 Changelog
 =========
 
+## [v26.25.3] - 2025-06-04
+### :sparkles: New Features
+- [`964b4a1`](https://github.com/tobymao/sqlglot/commit/964b4a1e367e00e243b80edf677cd48d453ed31e) - add line/col position for Star *(commit by [@georgesittas](https://github.com/georgesittas))*
+
+
 ## [v26.25.2] - 2025-06-04
 ### :sparkles: New Features
 - [`8b5129f`](https://github.com/tobymao/sqlglot/commit/8b5129f288880032f0bf9d649984d82314039af1) - **postgres**: improve pretty-formatting of ARRAY[...] *(commit by [@georgesittas](https://github.com/georgesittas))*
@@ -4788,3 +4793,4 @@ Changelog
 [v26.25.0]: https://github.com/tobymao/sqlglot/compare/v26.24.0...v26.25.0
 [v26.25.1]: https://github.com/tobymao/sqlglot/compare/v26.25.0...v26.25.1
 [v26.25.2]: https://github.com/tobymao/sqlglot/compare/v26.25.1...v26.25.2
+[v26.25.3]: https://github.com/tobymao/sqlglot/compare/v26.25.2...v26.25.3

README.md

@@ -497,6 +497,7 @@ See also: [Writing a Python SQL engine from scratch](https://github.com/tobymao/
 * [Dagster](https://github.com/dagster-io/dagster)
 * [Fugue](https://github.com/fugue-project/fugue)
 * [Ibis](https://github.com/ibis-project/ibis)
+* [dlt](https://github.com/dlt-hub/dlt)
 * [mysql-mimic](https://github.com/kelsin/mysql-mimic)
 * [Querybook](https://github.com/pinterest/querybook)
 * [Quokka](https://github.com/marsupialtail/quokka)

docs/sqlglot/_version.html

@@ -84,8 +84,8 @@
 </span><span id="L-17"><a href="#L-17"><span class="linenos">17</span></a><span class="n">__version_tuple__</span><span class="p">:</span> <span class="n">VERSION_TUPLE</span>
 </span><span id="L-18"><a href="#L-18"><span class="linenos">18</span></a><span class="n">version_tuple</span><span class="p">:</span> <span class="n">VERSION_TUPLE</span>
 </span><span id="L-19"><a href="#L-19"><span class="linenos">19</span></a>
-</span><span id="L-20"><a href="#L-20"><span class="linenos">20</span></a><span class="n">__version__</span> <span class="o">=</span> <span class="n">version</span> <span class="o">=</span> <span class="s1">&#39;26.25.2&#39;</span>
+</span><span id="L-20"><a href="#L-20"><span class="linenos">20</span></a><span class="n">__version__</span> <span class="o">=</span> <span class="n">version</span> <span class="o">=</span> <span class="s1">&#39;26.25.3&#39;</span>
-</span><span id="L-21"><a href="#L-21"><span class="linenos">21</span></a><span class="n">__version_tuple__</span> <span class="o">=</span> <span class="n">version_tuple</span> <span class="o">=</span> <span class="p">(</span><span class="mi">26</span><span class="p">,</span> <span class="mi">25</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
+</span><span id="L-21"><a href="#L-21"><span class="linenos">21</span></a><span class="n">__version_tuple__</span> <span class="o">=</span> <span class="n">version_tuple</span> <span class="o">=</span> <span class="p">(</span><span class="mi">26</span><span class="p">,</span> <span class="mi">25</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span>
 </span></pre></div>
 
 
@@ -93,7 +93,7 @@
                 <section id="__version__">
                     <div class="attr variable">
             <span class="name">__version__</span><span class="annotation">: str</span>        =
-<span class="default_value">&#39;26.25.2&#39;</span>
+<span class="default_value">&#39;26.25.3&#39;</span>
 
         
     </div>
@@ -105,7 +105,7 @@
                 <section id="__version_tuple__">
                     <div class="attr variable">
             <span class="name">__version_tuple__</span><span class="annotation">: object</span>        =
-<span class="default_value">(26, 25, 2)</span>
+<span class="default_value">(26, 25, 3)</span>
 
         
     </div>
@@ -117,7 +117,7 @@
                 <section id="version">
                     <div class="attr variable">
             <span class="name">version</span><span class="annotation">: str</span>        =
-<span class="default_value">&#39;26.25.2&#39;</span>
+<span class="default_value">&#39;26.25.3&#39;</span>
 
         
     </div>
@@ -129,7 +129,7 @@
                 <section id="version_tuple">
                     <div class="attr variable">
             <span class="name">version_tuple</span><span class="annotation">: object</span>        =
-<span class="default_value">(26, 25, 2)</span>
+<span class="default_value">(26, 25, 3)</span>
 
         
     </div>

docs/sqlglot/dialects.html

@@ -359,7 +359,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Athena">
                     <div class="attr variable">
             <span class="name">Athena</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634507837104&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571796728384&#39;&gt;</span>
 
         
     </div>
@@ -371,7 +371,7 @@ dialect implementations in order to understand how their various components can
                 <section id="BigQuery">
                     <div class="attr variable">
             <span class="name">BigQuery</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634507824912&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571796081632&#39;&gt;</span>
 
         
     </div>
@@ -383,7 +383,7 @@ dialect implementations in order to understand how their various components can
                 <section id="ClickHouse">
                     <div class="attr variable">
             <span class="name">ClickHouse</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634506710896&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571798395520&#39;&gt;</span>
 
         
     </div>
@@ -395,7 +395,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Databricks">
                     <div class="attr variable">
             <span class="name">Databricks</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634506014208&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571786944400&#39;&gt;</span>
 
         
     </div>
@@ -407,7 +407,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Doris">
                     <div class="attr variable">
             <span class="name">Doris</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634502703680&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571799701632&#39;&gt;</span>
 
         
     </div>
@@ -419,7 +419,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Drill">
                     <div class="attr variable">
             <span class="name">Drill</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634506225040&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571798507328&#39;&gt;</span>
 
         
     </div>
@@ -431,7 +431,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Druid">
                     <div class="attr variable">
             <span class="name">Druid</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634506216304&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571784920080&#39;&gt;</span>
 
         
     </div>
@@ -443,7 +443,7 @@ dialect implementations in order to understand how their various components can
                 <section id="DuckDB">
                     <div class="attr variable">
             <span class="name">DuckDB</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634494301136&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571784909808&#39;&gt;</span>
 
         
     </div>
@@ -455,7 +455,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Dune">
                     <div class="attr variable">
             <span class="name">Dune</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634505383792&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571785635072&#39;&gt;</span>
 
         
     </div>
@@ -467,7 +467,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Hive">
                     <div class="attr variable">
             <span class="name">Hive</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634502237920&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571796939552&#39;&gt;</span>
 
         
     </div>
@@ -479,7 +479,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Materialize">
                     <div class="attr variable">
             <span class="name">Materialize</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634509349440&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571796933216&#39;&gt;</span>
 
         
     </div>
@@ -491,7 +491,7 @@ dialect implementations in order to understand how their various components can
                 <section id="MySQL">
                     <div class="attr variable">
             <span class="name">MySQL</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634507150432&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571802007920&#39;&gt;</span>
 
         
     </div>
@@ -503,7 +503,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Oracle">
                     <div class="attr variable">
             <span class="name">Oracle</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634496723616&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571798015520&#39;&gt;</span>
 
         
     </div>
@@ -515,7 +515,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Postgres">
                     <div class="attr variable">
             <span class="name">Postgres</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634496715216&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571787331280&#39;&gt;</span>
 
         
     </div>
@@ -527,7 +527,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Presto">
                     <div class="attr variable">
             <span class="name">Presto</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634508955024&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571792711184&#39;&gt;</span>
 
         
     </div>
@@ -539,7 +539,7 @@ dialect implementations in order to understand how their various components can
                 <section id="PRQL">
                     <div class="attr variable">
             <span class="name">PRQL</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634507747792&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571790276352&#39;&gt;</span>
 
         
     </div>
@@ -551,7 +551,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Redshift">
                     <div class="attr variable">
             <span class="name">Redshift</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634504908416&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571796486896&#39;&gt;</span>
 
         
     </div>
@@ -563,7 +563,7 @@ dialect implementations in order to understand how their various components can
                 <section id="RisingWave">
                     <div class="attr variable">
             <span class="name">RisingWave</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634504916624&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571796480032&#39;&gt;</span>
 
         
     </div>
@@ -575,7 +575,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Snowflake">
                     <div class="attr variable">
             <span class="name">Snowflake</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634507238688&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571798302544&#39;&gt;</span>
 
         
     </div>
@@ -587,7 +587,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Spark">
                     <div class="attr variable">
             <span class="name">Spark</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634507369712&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571798306144&#39;&gt;</span>
 
         
     </div>
@@ -599,7 +599,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Spark2">
                     <div class="attr variable">
             <span class="name">Spark2</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634506022528&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571795407632&#39;&gt;</span>
 
         
     </div>
@@ -611,7 +611,7 @@ dialect implementations in order to understand how their various components can
                 <section id="SQLite">
                     <div class="attr variable">
             <span class="name">SQLite</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634506023632&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571791304560&#39;&gt;</span>
 
         
     </div>
@@ -623,7 +623,7 @@ dialect implementations in order to understand how their various components can
                 <section id="StarRocks">
                     <div class="attr variable">
             <span class="name">StarRocks</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634509005568&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571795611968&#39;&gt;</span>
 
         
     </div>
@@ -635,7 +635,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Tableau">
                     <div class="attr variable">
             <span class="name">Tableau</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634508366016&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571793529520&#39;&gt;</span>
 
         
     </div>
@@ -647,7 +647,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Teradata">
                     <div class="attr variable">
             <span class="name">Teradata</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634494650928&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571785251376&#39;&gt;</span>
 
         
     </div>
@@ -659,7 +659,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Trino">
                     <div class="attr variable">
             <span class="name">Trino</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634494658800&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571785259248&#39;&gt;</span>
 
         
     </div>
@@ -671,7 +671,7 @@ dialect implementations in order to understand how their various components can
                 <section id="TSQL">
                     <div class="attr variable">
             <span class="name">TSQL</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634494683168&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571785300000&#39;&gt;</span>
 
         
     </div>
@@ -683,7 +683,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Dialect">
                     <div class="attr variable">
             <span class="name">Dialect</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634494691088&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571785307920&#39;&gt;</span>
 
         
     </div>
@@ -695,7 +695,7 @@ dialect implementations in order to understand how their various components can
                 <section id="Dialects">
                     <div class="attr variable">
             <span class="name">Dialects</span>        =
-<span class="default_value">&lt;MagicMock id=&#39;140634494715456&#39;&gt;</span>
+<span class="default_value">&lt;MagicMock id=&#39;140571785332288&#39;&gt;</span>
 
         
     </div>

docs/sqlglot/expressions.html

@@ -63337,7 +63337,7 @@ Otherwise, this resets the expressions.</li>
                             <div id="DataType.STRUCT_TYPES" class="classattr">
                                 <div class="attr variable">
             <span class="name">STRUCT_TYPES</span>        =
-<span class="default_value">{&lt;Type.UNION: &#39;UNION&#39;&gt;, &lt;Type.OBJECT: &#39;OBJECT&#39;&gt;, &lt;Type.NESTED: &#39;NESTED&#39;&gt;, &lt;Type.STRUCT: &#39;STRUCT&#39;&gt;}</span>
+<span class="default_value">{&lt;Type.NESTED: &#39;NESTED&#39;&gt;, &lt;Type.UNION: &#39;UNION&#39;&gt;, &lt;Type.STRUCT: &#39;STRUCT&#39;&gt;, &lt;Type.OBJECT: &#39;OBJECT&#39;&gt;}</span>
 
         
     </div>
@@ -63349,7 +63349,7 @@ Otherwise, this resets the expressions.</li>
                             <div id="DataType.ARRAY_TYPES" class="classattr">
                                 <div class="attr variable">
             <span class="name">ARRAY_TYPES</span>        =
-<span class="default_value">{&lt;Type.LIST: &#39;LIST&#39;&gt;, &lt;Type.ARRAY: &#39;ARRAY&#39;&gt;}</span>
+<span class="default_value">{&lt;Type.ARRAY: &#39;ARRAY&#39;&gt;, &lt;Type.LIST: &#39;LIST&#39;&gt;}</span>
 
         
     </div>
@@ -63362,7 +63362,7 @@ Otherwise, this resets the expressions.</li>
                                 <div class="attr variable">
             <span class="name">NESTED_TYPES</span>        =
 <input id="DataType.NESTED_TYPES-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="DataType.NESTED_TYPES-view-value"></label><span class="default_value">{&lt;Type.MAP: &#39;MAP&#39;&gt;, &lt;Type.STRUCT: &#39;STRUCT&#39;&gt;, &lt;Type.LIST: &#39;LIST&#39;&gt;, &lt;Type.UNION: &#39;UNION&#39;&gt;, &lt;Type.OBJECT: &#39;OBJECT&#39;&gt;, &lt;Type.NESTED: &#39;NESTED&#39;&gt;, &lt;Type.ARRAY: &#39;ARRAY&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="DataType.NESTED_TYPES-view-value"></label><span class="default_value">{&lt;Type.OBJECT: &#39;OBJECT&#39;&gt;, &lt;Type.MAP: &#39;MAP&#39;&gt;, &lt;Type.LIST: &#39;LIST&#39;&gt;, &lt;Type.NESTED: &#39;NESTED&#39;&gt;, &lt;Type.UNION: &#39;UNION&#39;&gt;, &lt;Type.ARRAY: &#39;ARRAY&#39;&gt;, &lt;Type.STRUCT: &#39;STRUCT&#39;&gt;}</span>
 
         
     </div>
@@ -63375,7 +63375,7 @@ Otherwise, this resets the expressions.</li>
                                 <div class="attr variable">
             <span class="name">TEXT_TYPES</span>        =
 <input id="DataType.TEXT_TYPES-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="DataType.TEXT_TYPES-view-value"></label><span class="default_value">{&lt;Type.NAME: &#39;NAME&#39;&gt;, &lt;Type.VARCHAR: &#39;VARCHAR&#39;&gt;, &lt;Type.TEXT: &#39;TEXT&#39;&gt;, &lt;Type.NVARCHAR: &#39;NVARCHAR&#39;&gt;, &lt;Type.CHAR: &#39;CHAR&#39;&gt;, &lt;Type.NCHAR: &#39;NCHAR&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="DataType.TEXT_TYPES-view-value"></label><span class="default_value">{&lt;Type.NAME: &#39;NAME&#39;&gt;, &lt;Type.NVARCHAR: &#39;NVARCHAR&#39;&gt;, &lt;Type.VARCHAR: &#39;VARCHAR&#39;&gt;, &lt;Type.CHAR: &#39;CHAR&#39;&gt;, &lt;Type.NCHAR: &#39;NCHAR&#39;&gt;, &lt;Type.TEXT: &#39;TEXT&#39;&gt;}</span>
 
         
     </div>
@@ -63388,7 +63388,7 @@ Otherwise, this resets the expressions.</li>
                                 <div class="attr variable">
             <span class="name">SIGNED_INTEGER_TYPES</span>        =
 <input id="DataType.SIGNED_INTEGER_TYPES-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="DataType.SIGNED_INTEGER_TYPES-view-value"></label><span class="default_value">{&lt;Type.MEDIUMINT: &#39;MEDIUMINT&#39;&gt;, &lt;Type.INT128: &#39;INT128&#39;&gt;, &lt;Type.INT: &#39;INT&#39;&gt;, &lt;Type.INT256: &#39;INT256&#39;&gt;, &lt;Type.BIGINT: &#39;BIGINT&#39;&gt;, &lt;Type.SMALLINT: &#39;SMALLINT&#39;&gt;, &lt;Type.TINYINT: &#39;TINYINT&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="DataType.SIGNED_INTEGER_TYPES-view-value"></label><span class="default_value">{&lt;Type.MEDIUMINT: &#39;MEDIUMINT&#39;&gt;, &lt;Type.INT128: &#39;INT128&#39;&gt;, &lt;Type.BIGINT: &#39;BIGINT&#39;&gt;, &lt;Type.INT256: &#39;INT256&#39;&gt;, &lt;Type.SMALLINT: &#39;SMALLINT&#39;&gt;, &lt;Type.INT: &#39;INT&#39;&gt;, &lt;Type.TINYINT: &#39;TINYINT&#39;&gt;}</span>
 
         
     </div>
@@ -63401,7 +63401,7 @@ Otherwise, this resets the expressions.</li>
                                 <div class="attr variable">
             <span class="name">UNSIGNED_INTEGER_TYPES</span>        =
 <input id="DataType.UNSIGNED_INTEGER_TYPES-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="DataType.UNSIGNED_INTEGER_TYPES-view-value"></label><span class="default_value">{&lt;Type.UMEDIUMINT: &#39;UMEDIUMINT&#39;&gt;, &lt;Type.USMALLINT: &#39;USMALLINT&#39;&gt;, &lt;Type.UINT256: &#39;UINT256&#39;&gt;, &lt;Type.UINT: &#39;UINT&#39;&gt;, &lt;Type.UINT128: &#39;UINT128&#39;&gt;, &lt;Type.UTINYINT: &#39;UTINYINT&#39;&gt;, &lt;Type.UBIGINT: &#39;UBIGINT&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="DataType.UNSIGNED_INTEGER_TYPES-view-value"></label><span class="default_value">{&lt;Type.UMEDIUMINT: &#39;UMEDIUMINT&#39;&gt;, &lt;Type.UINT256: &#39;UINT256&#39;&gt;, &lt;Type.UINT128: &#39;UINT128&#39;&gt;, &lt;Type.USMALLINT: &#39;USMALLINT&#39;&gt;, &lt;Type.UTINYINT: &#39;UTINYINT&#39;&gt;, &lt;Type.UINT: &#39;UINT&#39;&gt;, &lt;Type.UBIGINT: &#39;UBIGINT&#39;&gt;}</span>
 
         
     </div>
@@ -63414,7 +63414,7 @@ Otherwise, this resets the expressions.</li>
                                 <div class="attr variable">
             <span class="name">INTEGER_TYPES</span>        =
 <input id="DataType.INTEGER_TYPES-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="DataType.INTEGER_TYPES-view-value"></label><span class="default_value">{&lt;Type.UMEDIUMINT: &#39;UMEDIUMINT&#39;&gt;, &lt;Type.BIT: &#39;BIT&#39;&gt;, &lt;Type.INT128: &#39;INT128&#39;&gt;, &lt;Type.MEDIUMINT: &#39;MEDIUMINT&#39;&gt;, &lt;Type.UBIGINT: &#39;UBIGINT&#39;&gt;, &lt;Type.USMALLINT: &#39;USMALLINT&#39;&gt;, &lt;Type.INT: &#39;INT&#39;&gt;, &lt;Type.UINT256: &#39;UINT256&#39;&gt;, &lt;Type.INT256: &#39;INT256&#39;&gt;, &lt;Type.BIGINT: &#39;BIGINT&#39;&gt;, &lt;Type.UINT: &#39;UINT&#39;&gt;, &lt;Type.UINT128: &#39;UINT128&#39;&gt;, &lt;Type.UTINYINT: &#39;UTINYINT&#39;&gt;, &lt;Type.SMALLINT: &#39;SMALLINT&#39;&gt;, &lt;Type.TINYINT: &#39;TINYINT&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="DataType.INTEGER_TYPES-view-value"></label><span class="default_value">{&lt;Type.UINT: &#39;UINT&#39;&gt;, &lt;Type.MEDIUMINT: &#39;MEDIUMINT&#39;&gt;, &lt;Type.INT128: &#39;INT128&#39;&gt;, &lt;Type.BIT: &#39;BIT&#39;&gt;, &lt;Type.BIGINT: &#39;BIGINT&#39;&gt;, &lt;Type.INT256: &#39;INT256&#39;&gt;, &lt;Type.SMALLINT: &#39;SMALLINT&#39;&gt;, &lt;Type.UMEDIUMINT: &#39;UMEDIUMINT&#39;&gt;, &lt;Type.UINT256: &#39;UINT256&#39;&gt;, &lt;Type.UINT128: &#39;UINT128&#39;&gt;, &lt;Type.USMALLINT: &#39;USMALLINT&#39;&gt;, &lt;Type.UTINYINT: &#39;UTINYINT&#39;&gt;, &lt;Type.INT: &#39;INT&#39;&gt;, &lt;Type.UBIGINT: &#39;UBIGINT&#39;&gt;, &lt;Type.TINYINT: &#39;TINYINT&#39;&gt;}</span>
 
         
     </div>
@@ -63439,7 +63439,7 @@ Otherwise, this resets the expressions.</li>
                                 <div class="attr variable">
             <span class="name">REAL_TYPES</span>        =
 <input id="DataType.REAL_TYPES-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="DataType.REAL_TYPES-view-value"></label><span class="default_value">{&lt;Type.DOUBLE: &#39;DOUBLE&#39;&gt;, &lt;Type.DECIMAL128: &#39;DECIMAL128&#39;&gt;, &lt;Type.UDOUBLE: &#39;UDOUBLE&#39;&gt;, &lt;Type.FLOAT: &#39;FLOAT&#39;&gt;, &lt;Type.BIGDECIMAL: &#39;BIGDECIMAL&#39;&gt;, &lt;Type.DECIMAL: &#39;DECIMAL&#39;&gt;, &lt;Type.DECIMAL64: &#39;DECIMAL64&#39;&gt;, &lt;Type.UDECIMAL: &#39;UDECIMAL&#39;&gt;, &lt;Type.SMALLMONEY: &#39;SMALLMONEY&#39;&gt;, &lt;Type.DECIMAL256: &#39;DECIMAL256&#39;&gt;, &lt;Type.MONEY: &#39;MONEY&#39;&gt;, &lt;Type.DECIMAL32: &#39;DECIMAL32&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="DataType.REAL_TYPES-view-value"></label><span class="default_value">{&lt;Type.DECIMAL256: &#39;DECIMAL256&#39;&gt;, &lt;Type.MONEY: &#39;MONEY&#39;&gt;, &lt;Type.DECIMAL32: &#39;DECIMAL32&#39;&gt;, &lt;Type.DOUBLE: &#39;DOUBLE&#39;&gt;, &lt;Type.DECIMAL: &#39;DECIMAL&#39;&gt;, &lt;Type.DECIMAL64: &#39;DECIMAL64&#39;&gt;, &lt;Type.UDECIMAL: &#39;UDECIMAL&#39;&gt;, &lt;Type.UDOUBLE: &#39;UDOUBLE&#39;&gt;, &lt;Type.BIGDECIMAL: &#39;BIGDECIMAL&#39;&gt;, &lt;Type.SMALLMONEY: &#39;SMALLMONEY&#39;&gt;, &lt;Type.FLOAT: &#39;FLOAT&#39;&gt;, &lt;Type.DECIMAL128: &#39;DECIMAL128&#39;&gt;}</span>
 
         
     </div>
@@ -63452,7 +63452,7 @@ Otherwise, this resets the expressions.</li>
                                 <div class="attr variable">
             <span class="name">NUMERIC_TYPES</span>        =
 <input id="DataType.NUMERIC_TYPES-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="DataType.NUMERIC_TYPES-view-value"></label><span class="default_value">{&lt;Type.DOUBLE: &#39;DOUBLE&#39;&gt;, &lt;Type.UMEDIUMINT: &#39;UMEDIUMINT&#39;&gt;, &lt;Type.BIT: &#39;BIT&#39;&gt;, &lt;Type.DECIMAL64: &#39;DECIMAL64&#39;&gt;, &lt;Type.UDECIMAL: &#39;UDECIMAL&#39;&gt;, &lt;Type.INT: &#39;INT&#39;&gt;, &lt;Type.SMALLMONEY: &#39;SMALLMONEY&#39;&gt;, &lt;Type.INT256: &#39;INT256&#39;&gt;, &lt;Type.UINT: &#39;UINT&#39;&gt;, &lt;Type.UINT128: &#39;UINT128&#39;&gt;, &lt;Type.MONEY: &#39;MONEY&#39;&gt;, &lt;Type.UTINYINT: &#39;UTINYINT&#39;&gt;, &lt;Type.UBIGINT: &#39;UBIGINT&#39;&gt;, &lt;Type.SMALLINT: &#39;SMALLINT&#39;&gt;, &lt;Type.TINYINT: &#39;TINYINT&#39;&gt;, &lt;Type.DECIMAL32: &#39;DECIMAL32&#39;&gt;, &lt;Type.DECIMAL128: &#39;DECIMAL128&#39;&gt;, &lt;Type.UDOUBLE: &#39;UDOUBLE&#39;&gt;, &lt;Type.FLOAT: &#39;FLOAT&#39;&gt;, &lt;Type.INT128: &#39;INT128&#39;&gt;, &lt;Type.MEDIUMINT: &#39;MEDIUMINT&#39;&gt;, &lt;Type.BIGDECIMAL: &#39;BIGDECIMAL&#39;&gt;, &lt;Type.USMALLINT: &#39;USMALLINT&#39;&gt;, &lt;Type.UINT256: &#39;UINT256&#39;&gt;, &lt;Type.DECIMAL: &#39;DECIMAL&#39;&gt;, &lt;Type.DECIMAL256: &#39;DECIMAL256&#39;&gt;, &lt;Type.BIGINT: &#39;BIGINT&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="DataType.NUMERIC_TYPES-view-value"></label><span class="default_value">{&lt;Type.INT128: &#39;INT128&#39;&gt;, &lt;Type.BIT: &#39;BIT&#39;&gt;, &lt;Type.BIGINT: &#39;BIGINT&#39;&gt;, &lt;Type.DECIMAL32: &#39;DECIMAL32&#39;&gt;, &lt;Type.UDOUBLE: &#39;UDOUBLE&#39;&gt;, &lt;Type.UINT: &#39;UINT&#39;&gt;, &lt;Type.UBIGINT: &#39;UBIGINT&#39;&gt;, &lt;Type.UDECIMAL: &#39;UDECIMAL&#39;&gt;, &lt;Type.DECIMAL128: &#39;DECIMAL128&#39;&gt;, &lt;Type.DECIMAL256: &#39;DECIMAL256&#39;&gt;, &lt;Type.MEDIUMINT: &#39;MEDIUMINT&#39;&gt;, &lt;Type.MONEY: &#39;MONEY&#39;&gt;, &lt;Type.INT256: &#39;INT256&#39;&gt;, &lt;Type.DOUBLE: &#39;DOUBLE&#39;&gt;, &lt;Type.SMALLINT: &#39;SMALLINT&#39;&gt;, &lt;Type.DECIMAL: &#39;DECIMAL&#39;&gt;, &lt;Type.UMEDIUMINT: &#39;UMEDIUMINT&#39;&gt;, &lt;Type.UINT256: &#39;UINT256&#39;&gt;, &lt;Type.DECIMAL64: &#39;DECIMAL64&#39;&gt;, &lt;Type.FLOAT: &#39;FLOAT&#39;&gt;, &lt;Type.UINT128: &#39;UINT128&#39;&gt;, &lt;Type.USMALLINT: &#39;USMALLINT&#39;&gt;, &lt;Type.UTINYINT: &#39;UTINYINT&#39;&gt;, &lt;Type.BIGDECIMAL: &#39;BIGDECIMAL&#39;&gt;, &lt;Type.SMALLMONEY: &#39;SMALLMONEY&#39;&gt;, &lt;Type.INT: &#39;INT&#39;&gt;, &lt;Type.TINYINT: &#39;TINYINT&#39;&gt;}</span>
 
         
     </div>
@@ -63465,7 +63465,7 @@ Otherwise, this resets the expressions.</li>
                                 <div class="attr variable">
             <span class="name">TEMPORAL_TYPES</span>        =
 <input id="DataType.TEMPORAL_TYPES-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="DataType.TEMPORAL_TYPES-view-value"></label><span class="default_value">{&lt;Type.DATETIME2: &#39;DATETIME2&#39;&gt;, &lt;Type.TIME: &#39;TIME&#39;&gt;, &lt;Type.TIMETZ: &#39;TIMETZ&#39;&gt;, &lt;Type.DATE: &#39;DATE&#39;&gt;, &lt;Type.DATE32: &#39;DATE32&#39;&gt;, &lt;Type.TIMESTAMPNTZ: &#39;TIMESTAMPNTZ&#39;&gt;, &lt;Type.TIMESTAMP_MS: &#39;TIMESTAMP_MS&#39;&gt;, &lt;Type.TIMESTAMP: &#39;TIMESTAMP&#39;&gt;, &lt;Type.TIMESTAMP_NS: &#39;TIMESTAMP_NS&#39;&gt;, &lt;Type.DATETIME: &#39;DATETIME&#39;&gt;, &lt;Type.TIMESTAMPLTZ: &#39;TIMESTAMPLTZ&#39;&gt;, &lt;Type.TIMESTAMP_S: &#39;TIMESTAMP_S&#39;&gt;, &lt;Type.DATETIME64: &#39;DATETIME64&#39;&gt;, &lt;Type.TIMESTAMPTZ: &#39;TIMESTAMPTZ&#39;&gt;, &lt;Type.SMALLDATETIME: &#39;SMALLDATETIME&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="DataType.TEMPORAL_TYPES-view-value"></label><span class="default_value">{&lt;Type.DATETIME: &#39;DATETIME&#39;&gt;, &lt;Type.DATETIME2: &#39;DATETIME2&#39;&gt;, &lt;Type.DATE: &#39;DATE&#39;&gt;, &lt;Type.DATE32: &#39;DATE32&#39;&gt;, &lt;Type.TIMESTAMPLTZ: &#39;TIMESTAMPLTZ&#39;&gt;, &lt;Type.DATETIME64: &#39;DATETIME64&#39;&gt;, &lt;Type.SMALLDATETIME: &#39;SMALLDATETIME&#39;&gt;, &lt;Type.TIMESTAMP: &#39;TIMESTAMP&#39;&gt;, &lt;Type.TIMESTAMPNTZ: &#39;TIMESTAMPNTZ&#39;&gt;, &lt;Type.TIMESTAMP_NS: &#39;TIMESTAMP_NS&#39;&gt;, &lt;Type.TIMESTAMPTZ: &#39;TIMESTAMPTZ&#39;&gt;, &lt;Type.TIMETZ: &#39;TIMETZ&#39;&gt;, &lt;Type.TIMESTAMP_MS: &#39;TIMESTAMP_MS&#39;&gt;, &lt;Type.TIMESTAMP_S: &#39;TIMESTAMP_S&#39;&gt;, &lt;Type.TIME: &#39;TIME&#39;&gt;}</span>
 
         
     </div>

docs/sqlglot/generator.html

@@ -12871,7 +12871,7 @@ Default: True</li>
                             <div id="Generator.PARAMETERIZABLE_TEXT_TYPES" class="classattr">
                                 <div class="attr variable">
             <span class="name">PARAMETERIZABLE_TEXT_TYPES</span>        =
-<span class="default_value">{&lt;Type.NVARCHAR: &#39;NVARCHAR&#39;&gt;, &lt;Type.CHAR: &#39;CHAR&#39;&gt;, &lt;Type.VARCHAR: &#39;VARCHAR&#39;&gt;, &lt;Type.NCHAR: &#39;NCHAR&#39;&gt;}</span>
+<span class="default_value">{&lt;Type.VARCHAR: &#39;VARCHAR&#39;&gt;, &lt;Type.NCHAR: &#39;NCHAR&#39;&gt;, &lt;Type.NVARCHAR: &#39;NVARCHAR&#39;&gt;, &lt;Type.CHAR: &#39;CHAR&#39;&gt;}</span>
 
         
     </div>

docs/sqlglot/helper.html

@@ -2003,7 +2003,7 @@ belong to some totally-ordered set.</p>
                 <section id="DATE_UNITS">
                     <div class="attr variable">
             <span class="name">DATE_UNITS</span>        =
-<span class="default_value">{&#39;year_month&#39;, &#39;year&#39;, &#39;day&#39;, &#39;month&#39;, &#39;quarter&#39;, &#39;week&#39;}</span>
+<span class="default_value">{&#39;day&#39;, &#39;year&#39;, &#39;year_month&#39;, &#39;quarter&#39;, &#39;week&#39;, &#39;month&#39;}</span>
 
         
     </div>

docs/sqlglot/optimizer/merge_subqueries.html

@@ -581,7 +581,7 @@ queries if it would result in multiple table selects in a single query:</p>
                     <div class="attr variable">
             <span class="name">UNMERGABLE_ARGS</span>        =
 <input id="UNMERGABLE_ARGS-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="UNMERGABLE_ARGS-view-value"></label><span class="default_value">{&#39;kind&#39;, &#39;laterals&#39;, &#39;locks&#39;, &#39;sort&#39;, &#39;limit&#39;, &#39;settings&#39;, &#39;qualify&#39;, &#39;distinct&#39;, &#39;with&#39;, &#39;match&#39;, &#39;pivots&#39;, &#39;having&#39;, &#39;sample&#39;, &#39;windows&#39;, &#39;operation_modifiers&#39;, &#39;offset&#39;, &#39;format&#39;, &#39;cluster&#39;, &#39;connect&#39;, &#39;into&#39;, &#39;options&#39;, &#39;prewhere&#39;, &#39;group&#39;, &#39;distribute&#39;}</span>
+            <label class="view-value-button pdoc-button" for="UNMERGABLE_ARGS-view-value"></label><span class="default_value">{&#39;options&#39;, &#39;qualify&#39;, &#39;group&#39;, &#39;locks&#39;, &#39;having&#39;, &#39;prewhere&#39;, &#39;kind&#39;, &#39;offset&#39;, &#39;cluster&#39;, &#39;distinct&#39;, &#39;operation_modifiers&#39;, &#39;settings&#39;, &#39;windows&#39;, &#39;limit&#39;, &#39;match&#39;, &#39;into&#39;, &#39;laterals&#39;, &#39;distribute&#39;, &#39;format&#39;, &#39;sample&#39;, &#39;connect&#39;, &#39;with&#39;, &#39;sort&#39;, &#39;pivots&#39;}</span>
 
         
     </div>

docs/sqlglot/optimizer/simplify.html

@@ -3285,7 +3285,7 @@ prefix are statically known.</p>
                 <section id="JOINS">
                     <div class="attr variable">
             <span class="name">JOINS</span>        =
-<span class="default_value">{(&#39;RIGHT&#39;, &#39;&#39;), (&#39;&#39;, &#39;INNER&#39;), (&#39;RIGHT&#39;, &#39;OUTER&#39;), (&#39;&#39;, &#39;&#39;)}</span>
+<span class="default_value">{(&#39;&#39;, &#39;&#39;), (&#39;RIGHT&#39;, &#39;OUTER&#39;), (&#39;RIGHT&#39;, &#39;&#39;), (&#39;&#39;, &#39;INNER&#39;)}</span>
 
         
     </div>

docs/sqlglot/tokens.html

@@ -9516,7 +9516,7 @@
                                 <div class="attr variable">
             <span class="name">TOKENS_PRECEDING_HINT</span>        =
 <input id="Tokenizer.TOKENS_PRECEDING_HINT-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="Tokenizer.TOKENS_PRECEDING_HINT-view-value"></label><span class="default_value">{&lt;<a href="#TokenType.INSERT">TokenType.INSERT</a>: &#39;INSERT&#39;&gt;, &lt;<a href="#TokenType.DELETE">TokenType.DELETE</a>: &#39;DELETE&#39;&gt;, &lt;<a href="#TokenType.UPDATE">TokenType.UPDATE</a>: &#39;UPDATE&#39;&gt;, &lt;<a href="#TokenType.SELECT">TokenType.SELECT</a>: &#39;SELECT&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="Tokenizer.TOKENS_PRECEDING_HINT-view-value"></label><span class="default_value">{&lt;<a href="#TokenType.SELECT">TokenType.SELECT</a>: &#39;SELECT&#39;&gt;, &lt;<a href="#TokenType.INSERT">TokenType.INSERT</a>: &#39;INSERT&#39;&gt;, &lt;<a href="#TokenType.UPDATE">TokenType.UPDATE</a>: &#39;UPDATE&#39;&gt;, &lt;<a href="#TokenType.DELETE">TokenType.DELETE</a>: &#39;DELETE&#39;&gt;}</span>
 
         
     </div>
@@ -9555,7 +9555,7 @@
                                 <div class="attr variable">
             <span class="name">COMMANDS</span>        =
 <input id="Tokenizer.COMMANDS-view-value" class="view-value-toggle-state" type="checkbox" aria-hidden="true" tabindex="-1">
-            <label class="view-value-button pdoc-button" for="Tokenizer.COMMANDS-view-value"></label><span class="default_value">{&lt;<a href="#TokenType.FETCH">TokenType.FETCH</a>: &#39;FETCH&#39;&gt;, &lt;<a href="#TokenType.COMMAND">TokenType.COMMAND</a>: &#39;COMMAND&#39;&gt;, &lt;<a href="#TokenType.SHOW">TokenType.SHOW</a>: &#39;SHOW&#39;&gt;, &lt;<a href="#TokenType.EXECUTE">TokenType.EXECUTE</a>: &#39;EXECUTE&#39;&gt;, &lt;<a href="#TokenType.RENAME">TokenType.RENAME</a>: &#39;RENAME&#39;&gt;}</span>
+            <label class="view-value-button pdoc-button" for="Tokenizer.COMMANDS-view-value"></label><span class="default_value">{&lt;<a href="#TokenType.EXECUTE">TokenType.EXECUTE</a>: &#39;EXECUTE&#39;&gt;, &lt;<a href="#TokenType.SHOW">TokenType.SHOW</a>: &#39;SHOW&#39;&gt;, &lt;<a href="#TokenType.RENAME">TokenType.RENAME</a>: &#39;RENAME&#39;&gt;, &lt;<a href="#TokenType.COMMAND">TokenType.COMMAND</a>: &#39;COMMAND&#39;&gt;, &lt;<a href="#TokenType.FETCH">TokenType.FETCH</a>: &#39;FETCH&#39;&gt;}</span>
 
         
     </div>

sqlglot/dialects/bigquery.py

@@ -525,6 +525,16 @@ class BigQuery(Dialect):
         LOG_DEFAULTS_TO_LN = True
         SUPPORTS_IMPLICIT_UNNEST = True
 
+        # BigQuery does not allow ASC/DESC to be used as an identifier
+        ID_VAR_TOKENS = parser.Parser.ID_VAR_TOKENS - {TokenType.ASC, TokenType.DESC}
+        ALIAS_TOKENS = parser.Parser.ALIAS_TOKENS - {TokenType.ASC, TokenType.DESC}
+        TABLE_ALIAS_TOKENS = parser.Parser.TABLE_ALIAS_TOKENS - {TokenType.ASC, TokenType.DESC}
+        COMMENT_TABLE_ALIAS_TOKENS = parser.Parser.COMMENT_TABLE_ALIAS_TOKENS - {
+            TokenType.ASC,
+            TokenType.DESC,
+        }
+        UPDATE_ALIAS_TOKENS = parser.Parser.UPDATE_ALIAS_TOKENS - {TokenType.ASC, TokenType.DESC}
+
         FUNCTIONS = {
             **parser.Parser.FUNCTIONS,
             "CONTAINS_SUBSTR": _build_contains_substring,

sqlglot/dialects/clickhouse.py

@@ -1096,6 +1096,7 @@ class ClickHouse(Dialect):
             exp.RegexpLike: lambda self, e: self.func("match", e.this, e.expression),
             exp.Rand: rename_func("randCanonical"),
             exp.StartsWith: rename_func("startsWith"),
+            exp.EndsWith: rename_func("endsWith"),
             exp.StrPosition: lambda self, e: strposition_sql(
                 self,
                 e,

sqlglot/dialects/postgres.py

@@ -36,6 +36,7 @@ from sqlglot.dialects.dialect import (
     strposition_sql,
     count_if_to_sum,
     groupconcat_sql,
+    Version,
 )
 from sqlglot.generator import unsupported_args
 from sqlglot.helper import is_int, seq_get
@@ -255,6 +256,15 @@ def _levenshtein_sql(self: Postgres.Generator, expression: exp.Levenshtein) -> s
     return rename_func(name)(self, expression)
 
 
+def _versioned_anyvalue_sql(self: Postgres.Generator, expression: exp.AnyValue) -> str:
+    # https://www.postgresql.org/docs/16/functions-aggregate.html
+    # https://www.postgresql.org/about/featurematrix/
+    if self.dialect.version < Version("16.0"):
+        return any_value_to_max_sql(self, expression)
+
+    return rename_func("ANY_VALUE")(self, expression)
+
+
 class Postgres(Dialect):
     INDEX_OFFSET = 1
     TYPED_DIVISION = True
@@ -546,7 +556,7 @@ class Postgres(Dialect):
 
         TRANSFORMS = {
             **generator.Generator.TRANSFORMS,
-            exp.AnyValue: any_value_to_max_sql,
+            exp.AnyValue: _versioned_anyvalue_sql,
             exp.ArrayConcat: lambda self, e: self.arrayconcat_sql(e, name="ARRAY_CAT"),
             exp.ArrayFilter: filter_array_using_unnest,
             exp.BitwiseXor: lambda self, e: self.binary(e, "#"),

sqlglot/dialects/risingwave.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 from sqlglot.dialects.postgres import Postgres
+from sqlglot.generator import Generator
 from sqlglot.tokens import TokenType
 import typing as t
 
@@ -72,3 +73,6 @@ class RisingWave(Postgres):
         }
 
         EXPRESSION_PRECEDES_PROPERTIES_CREATABLES = {"SINK"}
+
+        def computedcolumnconstraint_sql(self, expression: exp.ComputedColumnConstraint) -> str:
+            return Generator.computedcolumnconstraint_sql(self, expression)

sqlglot/dialects/snowflake.py

@@ -1019,6 +1019,7 @@ class Snowflake(Dialect):
             exp.ArgMin: rename_func("MIN_BY"),
             exp.ArrayConcat: lambda self, e: self.arrayconcat_sql(e, name="ARRAY_CAT"),
             exp.ArrayContains: lambda self, e: self.func("ARRAY_CONTAINS", e.expression, e.this),
+            exp.ArrayIntersect: rename_func("ARRAY_INTERSECTION"),
             exp.AtTimeZone: lambda self, e: self.func(
                 "CONVERT_TIMEZONE", e.args.get("zone"), e.this
             ),
@@ -1094,11 +1095,13 @@ class Snowflake(Dialect):
             exp.SHA: rename_func("SHA1"),
             exp.StarMap: rename_func("OBJECT_CONSTRUCT"),
             exp.StartsWith: rename_func("STARTSWITH"),
+            exp.EndsWith: rename_func("ENDSWITH"),
             exp.StrPosition: lambda self, e: strposition_sql(
                 self, e, func_name="CHARINDEX", supports_position=True
             ),
             exp.StrToDate: lambda self, e: self.func("DATE", e.this, self.format_time(e)),
             exp.Stuff: rename_func("INSERT"),
+            exp.StPoint: rename_func("ST_MAKEPOINT"),
             exp.TimeAdd: date_delta_sql("TIMEADD"),
             exp.Timestamp: no_timestamp_sql,
             exp.TimestampAdd: date_delta_sql("TIMESTAMPADD"),

sqlglot/dialects/spark.py

@@ -163,6 +163,7 @@ class Spark(Spark2):
                     move_partitioned_by_to_schema_columns,
                 ]
             ),
+            exp.EndsWith: rename_func("ENDSWITH"),
             exp.PartitionedByProperty: lambda self,
             e: f"PARTITIONED BY {self.wrap(self.expressions(sqls=[_normalize_partition(e) for e in e.this.expressions], skip_first=True))}",
             exp.StartsWith: rename_func("STARTSWITH"),

sqlglot/dialects/sqlite.py

@@ -99,6 +99,8 @@ class SQLite(Dialect):
         KEYWORDS = tokens.Tokenizer.KEYWORDS.copy()
         KEYWORDS.pop("/*+")
 
+        COMMANDS = {*tokens.Tokenizer.COMMANDS, TokenType.REPLACE}
+
     class Parser(parser.Parser):
         FUNCTIONS = {
             **parser.Parser.FUNCTIONS,
@@ -307,3 +309,10 @@ class SQLite(Dialect):
         @unsupported_args("this")
         def currentschema_sql(self, expression: exp.CurrentSchema) -> str:
             return "'main'"
+
+        def ignorenulls_sql(self, expression: exp.IgnoreNulls) -> str:
+            self.unsupported("SQLite does not support IGNORE NULLS.")
+            return self.sql(expression.this)
+
+        def respectnulls_sql(self, expression: exp.RespectNulls) -> str:
+            return self.sql(expression.this)

sqlglot/dialects/starrocks.py

@@ -17,6 +17,19 @@ from sqlglot.helper import seq_get
 from sqlglot.tokens import TokenType
 
 
+# https://docs.starrocks.io/docs/sql-reference/sql-functions/spatial-functions/st_distance_sphere/
+def st_distance_sphere(self, expression: exp.StDistance) -> str:
+    point1 = expression.this
+    point2 = expression.expression
+
+    point1_x = self.func("ST_X", point1)
+    point1_y = self.func("ST_Y", point1)
+    point2_x = self.func("ST_X", point2)
+    point2_y = self.func("ST_Y", point2)
+
+    return self.func("ST_Distance_Sphere", point1_x, point1_y, point2_x, point2_y)
+
+
 class StarRocks(MySQL):
     STRICT_JSON_PATH_SYNTAX = False
 
@@ -132,6 +145,8 @@ class StarRocks(MySQL):
         TRANSFORMS = {
             **MySQL.Generator.TRANSFORMS,
             exp.Array: inline_array_sql,
+            exp.ArrayAgg: rename_func("ARRAY_AGG"),
+            exp.ArrayFilter: rename_func("ARRAY_FILTER"),
             exp.ArrayToString: rename_func("ARRAY_JOIN"),
             exp.ApproxDistinct: approx_count_distinct_sql,
             exp.DateDiff: lambda self, e: self.func(
@@ -141,12 +156,12 @@ class StarRocks(MySQL):
             exp.JSONExtract: arrow_json_extract_sql,
             exp.Property: property_sql,
             exp.RegexpLike: rename_func("REGEXP"),
+            exp.StDistance: st_distance_sphere,
             exp.StrToUnix: lambda self, e: self.func("UNIX_TIMESTAMP", e.this, self.format_time(e)),
             exp.TimestampTrunc: lambda self, e: self.func("DATE_TRUNC", unit_to_str(e), e.this),
             exp.TimeStrToDate: rename_func("TO_DATE"),
             exp.UnixToStr: lambda self, e: self.func("FROM_UNIXTIME", e.this, self.format_time(e)),
             exp.UnixToTime: rename_func("FROM_UNIXTIME"),
-            exp.ArrayFilter: rename_func("ARRAY_FILTER"),
         }
 
         TRANSFORMS.pop(exp.DateTrunc)

sqlglot/expressions.py

@@ -31,6 +31,7 @@ from sqlglot.helper import (
     ensure_collection,
     ensure_list,
     seq_get,
+    split_num_words,
     subclasses,
     to_bool,
 )
@@ -1993,11 +1994,6 @@ class OnUpdateColumnConstraint(ColumnConstraintKind):
     pass
 
 
-# https://docs.snowflake.com/en/sql-reference/sql/create-external-table#optional-parameters
-class TransformColumnConstraint(ColumnConstraintKind):
-    pass
-
-
 class PrimaryKeyColumnConstraint(ColumnConstraintKind):
     arg_types = {"desc": False, "options": False}
 
@@ -5570,6 +5566,21 @@ class ArrayToString(Func):
     _sql_names = ["ARRAY_TO_STRING", "ARRAY_JOIN"]
 
 
+class ArrayIntersect(Func):
+    arg_types = {"expressions": True}
+    is_var_len_args = True
+    _sql_names = ["ARRAY_INTERSECT", "ARRAY_INTERSECTION"]
+
+
+class StPoint(Func):
+    arg_types = {"this": True, "expression": True, "null": False}
+    _sql_names = ["ST_POINT", "ST_MAKEPOINT"]
+
+
+class StDistance(Func):
+    arg_types = {"this": True, "expression": True, "use_spheroid": False}
+
+
 # https://cloud.google.com/bigquery/docs/reference/standard-sql/timestamp_functions#string
 class String(Func):
     arg_types = {"this": True, "zone": False}
@@ -6706,6 +6717,11 @@ class StartsWith(Func):
     arg_types = {"this": True, "expression": True}
 
 
+class EndsWith(Func):
+    _sql_names = ["ENDS_WITH", "ENDSWITH"]
+    arg_types = {"this": True, "expression": True}
+
+
 class StrPosition(Func):
     arg_types = {
         "this": True,
@@ -7366,7 +7382,7 @@ def _apply_set_operation(
     **opts,
 ) -> S:
     return reduce(
-        lambda x, y: set_operation(this=x, expression=y, distinct=distinct),
+        lambda x, y: set_operation(this=x, expression=y, distinct=distinct, **opts),
         (maybe_parse(e, dialect=dialect, copy=copy, **opts) for e in expressions),
     )
 
@@ -7962,7 +7978,15 @@ def to_table(
     if isinstance(sql_path, Table):
         return maybe_copy(sql_path, copy=copy)
 
-    table = maybe_parse(sql_path, into=Table, dialect=dialect)
+    try:
+        table = maybe_parse(sql_path, into=Table, dialect=dialect)
+    except ParseError:
+        catalog, db, this = split_num_words(sql_path, ".", 3)
+
+        if not this:
+            raise
+
+        table = table_(this, db=db, catalog=catalog)
 
     for k, v in kwargs.items():
         table.set(k, v)
@@ -8110,7 +8134,7 @@ def column(
 
 @t.overload
 def column(
-    col: str | Identifier,
+    col: str | Identifier | Star,
     table: t.Optional[str | Identifier] = None,
     db: t.Optional[str | Identifier] = None,
     catalog: t.Optional[str | Identifier] = None,
@@ -8147,8 +8171,11 @@ def column(
     Returns:
         The new Column instance.
     """
+    if not isinstance(col, Star):
+        col = to_identifier(col, quoted=quoted, copy=copy)
+
     this = Column(
-        this=to_identifier(col, quoted=quoted, copy=copy),
+        this=col,
         table=to_identifier(table, quoted=quoted, copy=copy),
         db=to_identifier(db, quoted=quoted, copy=copy),
         catalog=to_identifier(catalog, quoted=quoted, copy=copy),

sqlglot/generator.py

@@ -1018,6 +1018,7 @@ class Generator(metaclass=_Generator):
             persisted = " PERSISTED"
         else:
             persisted = ""
+
         return f"AS {this}{persisted}"
 
     def autoincrementcolumnconstraint_sql(self, _) -> str:
@@ -1079,9 +1080,6 @@ class Generator(metaclass=_Generator):
     def notnullcolumnconstraint_sql(self, expression: exp.NotNullColumnConstraint) -> str:
         return f"{'' if expression.args.get('allow_null') else 'NOT '}NULL"
 
-    def transformcolumnconstraint_sql(self, expression: exp.TransformColumnConstraint) -> str:
-        return f"AS {self.sql(expression, 'this')}"
-
     def primarykeycolumnconstraint_sql(self, expression: exp.PrimaryKeyColumnConstraint) -> str:
         desc = expression.args.get("desc")
         if desc is not None:

sqlglot/parser.py

@@ -936,6 +936,7 @@ class Parser(metaclass=_Parser):
         "ORDER BY": lambda self, query: query.order_by(self._parse_order(), copy=False),
         "LIMIT": lambda self, query: self._parse_pipe_syntax_limit(query),
         "OFFSET": lambda self, query: query.offset(self._parse_offset(), copy=False),
+        "AGGREGATE": lambda self, query: self._parse_pipe_syntax_aggregate(query),
     }
 
     PROPERTY_PARSERS: t.Dict[str, t.Callable] = {
@@ -1143,6 +1144,78 @@ class Parser(metaclass=_Parser):
             query.offset(offset, copy=False)
         return query
 
+    def _parse_pipe_syntax_aggregate_fields(self) -> t.Optional[exp.Expression]:
+        this = self._parse_assignment()
+        if self._match_text_seq("GROUP", "AND", advance=False):
+            return this
+
+        this = self._parse_alias(this)
+
+        if self._match_set((TokenType.ASC, TokenType.DESC), advance=False):
+            return self._parse_ordered(lambda: this)
+
+        return this
+
+    def _parse_pipe_syntax_aggregate_group_order_by(
+        self, query: exp.Query, group_by_exists: bool = True
+    ) -> exp.Query:
+        expr = self._parse_csv(self._parse_pipe_syntax_aggregate_fields)
+        aggregates_or_groups, orders = [], []
+        for element in expr:
+            if isinstance(element, exp.Ordered):
+                this = element.this
+                if isinstance(this, exp.Alias):
+                    element.set("this", this.args["alias"])
+                orders.append(element)
+            else:
+                this = element
+            aggregates_or_groups.append(this)
+
+        if group_by_exists and isinstance(query, exp.Select):
+            query = query.select(*aggregates_or_groups, copy=False).group_by(
+                *[element.args.get("alias", element) for element in aggregates_or_groups],
+                copy=False,
+            )
+        else:
+            query = exp.select(*aggregates_or_groups, copy=False).from_(
+                query.subquery(copy=False), copy=False
+            )
+
+        if orders:
+            return query.order_by(*orders, copy=False)
+
+        return query
+
+    def _parse_pipe_syntax_aggregate(self, query: exp.Query) -> exp.Query:
+        self._match_text_seq("AGGREGATE")
+        query = self._parse_pipe_syntax_aggregate_group_order_by(query, group_by_exists=False)
+
+        if self._match(TokenType.GROUP_BY) or (
+            self._match_text_seq("GROUP", "AND") and self._match(TokenType.ORDER_BY)
+        ):
+            return self._parse_pipe_syntax_aggregate_group_order_by(query)
+
+        return query
+
+    def _parse_pipe_syntax_set_operator(
+        self, query: t.Optional[exp.Query]
+    ) -> t.Optional[exp.Query]:
+        first_setop = self.parse_set_operation(this=query)
+
+        if not first_setop or not query:
+            return None
+
+        first_setop.this.pop()
+        distinct = first_setop.args.pop("distinct")
+
+        setops = [first_setop.expression.pop(), *self._parse_expressions()]
+
+        if isinstance(first_setop, exp.Union):
+            return query.union(*setops, distinct=distinct, **first_setop.args)
+        if isinstance(first_setop, exp.Except):
+            return query.except_(*setops, distinct=distinct, **first_setop.args)
+        return query.intersect(*setops, distinct=distinct, **first_setop.args)
+
     def _parse_partitioned_by_bucket_or_truncate(self) -> exp.Expression:
         klass = (
             exp.PartitionedByBucket
@@ -5900,7 +5973,7 @@ class Parser(metaclass=_Parser):
             constraints.append(
                 self.expression(
                     exp.ColumnConstraint,
-                    kind=exp.TransformColumnConstraint(this=self._parse_disjunction()),
+                    kind=exp.ComputedColumnConstraint(this=self._parse_disjunction()),
                 )
             )
 
@@ -7163,11 +7236,18 @@ class Parser(metaclass=_Parser):
 
         return this
 
-    def _parse_pipe_syntax_query(self, query: exp.Select) -> exp.Query:
+    def _parse_pipe_syntax_query(self, query: exp.Query) -> t.Optional[exp.Query]:
         while self._match(TokenType.PIPE_GT):
+            start = self._curr
             parser = self.PIPE_SYNTAX_TRANSFORM_PARSERS.get(self._curr.text.upper())
             if not parser:
-                self.raise_error(f"Unsupported pipe syntax operator: '{self._curr.text.upper()}'.")
+                set_op_query = self._parse_pipe_syntax_set_operator(query)
+                if not set_op_query:
+                    self._retreat(start)
+                    self.raise_error(f"Unsupported pipe syntax operator: '{start.text.upper()}'.")
+                    break
+
+                query = set_op_query
             else:
                 query = parser(self, query)
 

sqlglotrs/src/token.rs

@@ -1,7 +1,7 @@
 use crate::settings::TokenType;
 use pyo3::prelude::*;
 use pyo3::types::{PyList, PyString};
-use pyo3::{pyclass, Py, PyObject, Python};
+use pyo3::{pyclass, pymethods, Py, PyObject, Python};
 
 #[derive(Debug)]
 #[pyclass]
@@ -57,3 +57,25 @@ impl Token {
         });
     }
 }
+
+#[pymethods]
+impl Token {
+    fn __repr__(&self, py: Python) -> PyResult<String> {
+        let text = self.text.bind(py).to_str()?;
+        let comments = self.comments.bind(py);
+        let token_type_str = self.token_type_py.bind(py).str()?;
+        let comments_repr = comments.repr()?;
+        let comments_str = comments_repr.to_str()?;
+
+        Ok(format!(
+            "<Token token_type: {}, text: {}, line: {}, col: {}, start: {}, end: {}, comments: {}>",
+            token_type_str,
+            text,
+            self.line,
+            self.col,
+            self.start,
+            self.end,
+            comments_str
+        ))
+    }
+}

tests/dialects/test_dialect.py

@@ -462,6 +462,16 @@ class TestDialect(Validator):
             "CAST('127.0.0.1/32' AS INET)",
             read={"postgres": "INET '127.0.0.1/32'"},
         )
+        self.assertIsNotNone(
+            self.validate_identity("CREATE TABLE foo (bar INT AS (foo))").find(
+                exp.ComputedColumnConstraint
+            )
+        )
+        self.assertIsNotNone(
+            self.validate_identity(
+                "CREATE TABLE foo (t1 INT, t2 INT, bar INT AS (t1 * t2 * 2))"
+            ).find(exp.ComputedColumnConstraint)
+        )
 
     def test_ddl(self):
         self.validate_all(
@@ -1304,6 +1314,32 @@ class TestDialect(Validator):
             },
         )
 
+        self.validate_all(
+            "ARRAY_INTERSECT(x, y)",
+            read={
+                "hive": "ARRAY_INTERSECT(x, y)",
+                "spark2": "ARRAY_INTERSECT(x, y)",
+                "spark": "ARRAY_INTERSECT(x, y)",
+                "databricks": "ARRAY_INTERSECT(x, y)",
+                "presto": "ARRAY_INTERSECT(x, y)",
+                "trino": "ARRAY_INTERSECT(x, y)",
+                "snowflake": "ARRAY_INTERSECTION(x, y)",
+                "starrocks": "ARRAY_INTERSECT(x, y)",
+            },
+            write={
+                "hive": "ARRAY_INTERSECT(x, y)",
+                "spark2": "ARRAY_INTERSECT(x, y)",
+                "spark": "ARRAY_INTERSECT(x, y)",
+                "databricks": "ARRAY_INTERSECT(x, y)",
+                "presto": "ARRAY_INTERSECT(x, y)",
+                "trino": "ARRAY_INTERSECT(x, y)",
+                "snowflake": "ARRAY_INTERSECTION(x, y)",
+                "starrocks": "ARRAY_INTERSECT(x, y)",
+            },
+        )
+
+        self.validate_identity("SELECT ARRAY_INTERSECT(x, y, z)")
+
     def test_order_by(self):
         self.validate_identity(
             "SELECT c FROM t ORDER BY a, b,",
@@ -3528,3 +3564,81 @@ FROM subquery2""",
                     f"FROM x |> SELECT x1, x2 |> WHERE x1 > 0 |> WHERE x2 > 0  |> ORDER BY x1, x2 |> {option}",
                     f"SELECT x1, x2 FROM (SELECT * FROM x) WHERE x1 > 0 AND x2 > 0 ORDER BY x1, x2 {option}",
                 )
+        self.validate_identity(
+            "FROM x |> AGGREGATE SUM(x1), MAX(x2), MIN(x3)",
+            "SELECT SUM(x1), MAX(x2), MIN(x3) FROM (SELECT * FROM x)",
+        )
+        self.validate_identity(
+            "FROM x |> AGGREGATE SUM(x1) AS s_x1 |> SELECT s_x1",
+            "SELECT s_x1 FROM (SELECT SUM(x1) AS s_x1 FROM (SELECT * FROM x))",
+        )
+        self.validate_identity(
+            "FROM x |> AGGREGATE SUM(x1), MAX(x2), MIN(x3) GROUP BY x4, x5",
+            "SELECT SUM(x1), MAX(x2), MIN(x3), x4, x5 FROM (SELECT * FROM x) GROUP BY x4, x5",
+        )
+        self.validate_identity(
+            "FROM x |> AGGREGATE SUM(x1), MAX(x2), MIN(x3) GROUP BY x4 AS a_x4, x5 AS a_x5",
+            "SELECT SUM(x1), MAX(x2), MIN(x3), x4 AS a_x4, x5 AS a_x5 FROM (SELECT * FROM x) GROUP BY a_x4, a_x5",
+        )
+        self.validate_identity(
+            "FROM x |> AGGREGATE SUM(x1) as s_x1 GROUP BY x1 |> SELECT s_x1, x1 as ss_x1",
+            "SELECT s_x1, x1 AS ss_x1 FROM (SELECT SUM(x1) AS s_x1, x1 FROM (SELECT * FROM x) GROUP BY x1)",
+        )
+        self.validate_identity(
+            "FROM x |> AGGREGATE SUM(x1) GROUP", "SELECT SUM(x1) AS GROUP FROM (SELECT * FROM x)"
+        )
+        for order_option in ("ASC", "DESC", "ASC NULLS LAST", "DESC NULLS FIRST"):
+            with self.subTest(f"Testing pipe syntax AGGREGATE for order option: {order_option}"):
+                self.validate_all(
+                    f"SELECT SUM(x1) AS x_s FROM (SELECT * FROM x) ORDER BY x_s {order_option}",
+                    read={
+                        "bigquery": f"FROM x |> AGGREGATE SUM(x1) AS x_s {order_option}",
+                    },
+                )
+                self.validate_all(
+                    f"SELECT SUM(x1) AS x_s, x1 AS g_x1 FROM (SELECT * FROM x) GROUP BY g_x1 ORDER BY x_s {order_option}",
+                    read={
+                        "bigquery": f"FROM x |> AGGREGATE SUM(x1) AS x_s {order_option} GROUP BY x1 AS g_x1",
+                    },
+                )
+            with self.subTest(
+                f"Testing pipe syntax AGGREGATE with GROUP AND ORDER BY for order option: {order_option}"
+            ):
+                self.validate_all(
+                    f"SELECT g_x1, x_s FROM (SELECT SUM(x1) AS x_s, x1 AS g_x1 FROM (SELECT * FROM x) GROUP BY g_x1 ORDER BY g_x1 {order_option})",
+                    read={
+                        "bigquery": f"FROM x |> AGGREGATE SUM(x1) AS x_s GROUP AND ORDER BY x1 AS g_x1 {order_option} |> SELECT g_x1, x_s",
+                    },
+                )
+
+            for op_operator in (
+                "UNION ALL",
+                "UNION DISTINCT",
+                "INTERSECT DISTINCT",
+                "EXCEPT DISTINCT",
+            ):
+                with self.subTest(f"Testing pipe syntax SET OPERATORS: {op_operator}"):
+                    self.validate_all(
+                        f"FROM x|> {op_operator} (SELECT y1 FROM y), (SELECT z1 FROM z)",
+                        write={
+                            "bigquery": f"SELECT * FROM x {op_operator} (SELECT y1 FROM y) {op_operator} (SELECT z1 FROM z)",
+                        },
+                    )
+
+            for op_prefix in ("LEFT OUTER", "FULL OUTER"):
+                for op_operator in (
+                    "UNION ALL",
+                    "UNION DISTINCT",
+                    "INTERSECT DISTINCT",
+                    "EXCEPT DISTINCT",
+                ):
+                    for suffix_operator in ("BY NAME", "CORRESPONDING"):
+                        with self.subTest(
+                            f"Testing pipe syntax SET OPERATORS: {op_prefix} {op_operator} {suffix_operator}"
+                        ):
+                            self.validate_all(
+                                f"FROM x|> SELECT x1, x2 FROM x |> {op_prefix} {op_operator} {suffix_operator} (SELECT y1, y2 FROM y), (SELECT z1, z2 FROM z)",
+                                write={
+                                    "bigquery": f"SELECT x1, x2 FROM (SELECT * FROM x) {op_prefix} {op_operator} BY NAME (SELECT y1, y2 FROM y) {op_prefix} {op_operator} BY NAME (SELECT z1, z2 FROM z)",
+                                },
+                            )

tests/dialects/test_duckdb.py

@@ -9,13 +9,6 @@ class TestDuckDB(Validator):
     dialect = "duckdb"
 
     def test_duckdb(self):
-        self.validate_identity("SELECT * FROM my_ducklake.demo AT (VERSION => 2)")
-        self.validate_identity("SELECT UUIDV7()")
-        self.validate_identity("SELECT TRY(LOG(0))")
-        self.validate_identity("x::timestamp", "CAST(x AS TIMESTAMP)")
-        self.validate_identity("x::timestamp without time zone", "CAST(x AS TIMESTAMP)")
-        self.validate_identity("x::timestamp with time zone", "CAST(x AS TIMESTAMPTZ)")
-
         with self.assertRaises(ParseError):
             parse_one("1 //", read="duckdb")
 
@@ -36,6 +29,20 @@ class TestDuckDB(Validator):
             "STRUCT(k TEXT, v STRUCT(v_str TEXT, v_int INT, v_int_arr INT[]))[]",
         )
 
+        self.validate_all(
+            "SELECT FIRST_VALUE(c IGNORE NULLS) OVER (PARTITION BY gb ORDER BY ob) FROM t",
+            write={
+                "duckdb": "SELECT FIRST_VALUE(c IGNORE NULLS) OVER (PARTITION BY gb ORDER BY ob) FROM t",
+                "sqlite": UnsupportedError,
+            },
+        )
+        self.validate_all(
+            "SELECT FIRST_VALUE(c RESPECT NULLS) OVER (PARTITION BY gb ORDER BY ob) FROM t",
+            write={
+                "duckdb": "SELECT FIRST_VALUE(c RESPECT NULLS) OVER (PARTITION BY gb ORDER BY ob) FROM t",
+                "sqlite": "SELECT FIRST_VALUE(c) OVER (PARTITION BY gb ORDER BY ob NULLS LAST) FROM t",
+            },
+        )
         self.validate_all(
             "CAST(x AS UUID)",
             write={
@@ -264,6 +271,12 @@ class TestDuckDB(Validator):
             parse_one("a // b", read="duckdb").assert_is(exp.IntDiv).sql(dialect="duckdb"), "a // b"
         )
 
+        self.validate_identity("SELECT * FROM my_ducklake.demo AT (VERSION => 2)")
+        self.validate_identity("SELECT UUIDV7()")
+        self.validate_identity("SELECT TRY(LOG(0))")
+        self.validate_identity("x::timestamp", "CAST(x AS TIMESTAMP)")
+        self.validate_identity("x::timestamp without time zone", "CAST(x AS TIMESTAMP)")
+        self.validate_identity("x::timestamp with time zone", "CAST(x AS TIMESTAMPTZ)")
         self.validate_identity("CAST(x AS FOO)")
         self.validate_identity("SELECT UNNEST([1, 2])").selects[0].assert_is(exp.UDTF)
         self.validate_identity("'red' IN flags").args["field"].assert_is(exp.Column)

tests/dialects/test_postgres.py

@@ -22,6 +22,7 @@ class TestPostgres(Validator):
         expected_sql = "ARRAY[\n  x" + (",\n  x" * 27) + "\n]"
         self.validate_identity(sql, expected_sql, pretty=True)
 
+        self.validate_identity("SELECT ST_DISTANCE(gg1, gg2, FALSE) AS sphere_dist")
         self.validate_identity("SHA384(x)")
         self.validate_identity("1.x", "1. AS x")
         self.validate_identity("|/ x", "SQRT(x)")
@@ -908,6 +909,18 @@ FROM json_data, field_ids""",
             },
         )
 
+        # Postgres introduced ANY_VALUE in version 16
+        self.validate_all(
+            "SELECT ANY_VALUE(1) AS col",
+            write={
+                "postgres": "SELECT ANY_VALUE(1) AS col",
+                "postgres, version=16": "SELECT ANY_VALUE(1) AS col",
+                "postgres, version=17.5": "SELECT ANY_VALUE(1) AS col",
+                "postgres, version=15": "SELECT MAX(1) AS col",
+                "postgres, version=13.9": "SELECT MAX(1) AS col",
+            },
+        )
+
     def test_ddl(self):
         # Checks that user-defined types are parsed into DataType instead of Identifier
         self.parse_one("CREATE TABLE t (a udt)").this.expressions[0].args["kind"].assert_is(

tests/dialects/test_presto.py

@@ -778,7 +778,7 @@ class TestPresto(Validator):
                 "hive": "FIRST(x)",
                 "mysql": "ANY_VALUE(x)",
                 "oracle": "ANY_VALUE(x)",
-                "postgres": "MAX(x)",
+                "postgres": "ANY_VALUE(x)",
                 "presto": "ARBITRARY(x)",
                 "redshift": "ANY_VALUE(x)",
                 "snowflake": "ANY_VALUE(x)",

tests/dialects/test_snowflake.py

@@ -318,6 +318,13 @@ class TestSnowflake(Validator):
             "SELECT * FROM xxx, yyy, zzz",
         )
 
+        self.validate_all(
+            "SELECT ARRAY_INTERSECTION([1, 2], [2, 3])",
+            write={
+                "starrocks": "SELECT ARRAY_INTERSECT([1, 2], [2, 3])",
+            },
+        )
+
         self.validate_all(
             "CREATE TABLE test_table (id NUMERIC NOT NULL AUTOINCREMENT)",
             write={
@@ -1079,6 +1086,22 @@ class TestSnowflake(Validator):
             },
         )
 
+        self.validate_all(
+            "SELECT ST_MAKEPOINT(10, 20)",
+            write={
+                "snowflake": "SELECT ST_MAKEPOINT(10, 20)",
+                "starrocks": "SELECT ST_POINT(10, 20)",
+            },
+        )
+
+        self.validate_all(
+            "SELECT ST_DISTANCE(a, b)",
+            write={
+                "snowflake": "SELECT ST_DISTANCE(a, b)",
+                "starrocks": "SELECT ST_DISTANCE_SPHERE(ST_X(a), ST_Y(a), ST_X(b), ST_Y(b))",
+            },
+        )
+
     def test_null_treatment(self):
         self.validate_all(
             r"SELECT FIRST_VALUE(TABLE1.COLUMN1) OVER (PARTITION BY RANDOM_COLUMN1, RANDOM_COLUMN2 ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS MY_ALIAS FROM TABLE1",
@@ -1687,12 +1710,6 @@ class TestSnowflake(Validator):
                     },
                 )
 
-        self.assertIsNotNone(
-            self.validate_identity("CREATE TABLE foo (bar INT AS (foo))").find(
-                exp.TransformColumnConstraint
-            )
-        )
-
     def test_user_defined_functions(self):
         self.validate_all(
             "CREATE FUNCTION a(x DATE, y BIGINT) RETURNS ARRAY LANGUAGE JAVASCRIPT AS $$ SELECT 1 $$",
@@ -2013,6 +2030,26 @@ FROM persons AS p, LATERAL FLATTEN(input => p.c, path => 'contact') AS _flattene
                 "spark": "DESCRIBE db.table",
             },
         )
+        self.validate_all(
+            "ENDSWITH('abc', 'c')",
+            read={
+                "bigquery": "ENDS_WITH('abc', 'c')",
+                "clickhouse": "endsWith('abc', 'c')",
+                "databricks": "ENDSWITH('abc', 'c')",
+                "duckdb": "ENDS_WITH('abc', 'c')",
+                "presto": "ENDS_WITH('abc', 'c')",
+                "spark": "ENDSWITH('abc', 'c')",
+            },
+            write={
+                "bigquery": "ENDS_WITH('abc', 'c')",
+                "clickhouse": "endsWith('abc', 'c')",
+                "databricks": "ENDSWITH('abc', 'c')",
+                "duckdb": "ENDS_WITH('abc', 'c')",
+                "presto": "ENDS_WITH('abc', 'c')",
+                "snowflake": "ENDSWITH('abc', 'c')",
+                "spark": "ENDSWITH('abc', 'c')",
+            },
+        )
 
     def test_parse_like_any(self):
         like = parse_one("a LIKE ANY fun('foo')", read="snowflake")

tests/dialects/test_sqlite.py

@@ -113,6 +113,7 @@ class TestSQLite(Validator):
             'CREATE TABLE "foo t" ("foo t id" TEXT NOT NULL, PRIMARY KEY ("foo t id"))',
             'CREATE TABLE "foo t" ("foo t id" TEXT NOT NULL PRIMARY KEY)',
         )
+        self.validate_identity("REPLACE INTO foo (x, y) VALUES (1, 2)", check_command_warning=True)
 
     def test_strftime(self):
         self.validate_identity("SELECT STRFTIME('%Y/%m/%d', 'now')")

tests/dialects/test_starrocks.py

@@ -9,6 +9,9 @@ class TestStarrocks(Validator):
         self.validate_identity("SELECT ARRAY_JOIN([1, 3, 5, NULL], '_', 'NULL')")
         self.validate_identity("SELECT ARRAY_JOIN([1, 3, 5, NULL], '_')")
         self.validate_identity("ALTER TABLE a SWAP WITH b")
+        self.validate_identity("SELECT ARRAY_AGG(a) FROM x")
+        self.validate_identity("SELECT ST_POINT(10, 20)")
+        self.validate_identity("SELECT ST_DISTANCE_SPHERE(10.1, 20.2, 30.3, 40.4)")
 
     def test_ddl(self):
         ddl_sqls = [

tests/test_expressions.py

@@ -669,6 +669,8 @@ class TestExpressions(unittest.TestCase):
         self.assertIsInstance(parse_one("ARRAY_AGG(a)"), exp.ArrayAgg)
         self.assertIsInstance(parse_one("ARRAY_CONTAINS(a, 'a')"), exp.ArrayContains)
         self.assertIsInstance(parse_one("ARRAY_SIZE(a)"), exp.ArraySize)
+        self.assertIsInstance(parse_one("ARRAY_INTERSECTION([1, 2], [2, 3])"), exp.ArrayIntersect)
+        self.assertIsInstance(parse_one("ARRAY_INTERSECT([1, 2], [2, 3])"), exp.ArrayIntersect)
         self.assertIsInstance(parse_one("AVG(a)"), exp.Avg)
         self.assertIsInstance(parse_one("BEGIN DEFERRED TRANSACTION"), exp.Transaction)
         self.assertIsInstance(parse_one("CEIL(a)"), exp.Ceil)
@@ -710,6 +712,8 @@ class TestExpressions(unittest.TestCase):
         self.assertIsInstance(parse_one("ROUND(a)"), exp.Round)
         self.assertIsInstance(parse_one("ROUND(a, 2)"), exp.Round)
         self.assertIsInstance(parse_one("SPLIT(a, 'test')"), exp.Split)
+        self.assertIsInstance(parse_one("ST_POINT(10, 20)"), exp.StPoint)
+        self.assertIsInstance(parse_one("ST_DISTANCE(a, b)"), exp.StDistance)
         self.assertIsInstance(parse_one("STR_POSITION(a, 'test')"), exp.StrPosition)
         self.assertIsInstance(parse_one("STR_TO_UNIX(a, 'format')"), exp.StrToUnix)
         self.assertIsInstance(parse_one("STRUCT_EXTRACT(a, 'test')"), exp.StructExtract)
@@ -752,6 +756,9 @@ class TestExpressions(unittest.TestCase):
         self.assertIsInstance(parse_one("ADD_MONTHS(a, b)"), exp.AddMonths)
 
     def test_column(self):
+        column = exp.column(exp.Star(), table="t")
+        self.assertEqual(column.sql(), "t.*")
+
         column = parse_one("a.b.c.d")
         self.assertEqual(column.catalog, "a")
         self.assertEqual(column.db, "b")
@@ -987,15 +994,20 @@ FROM foo""",
         self.assertEqual(table_only.name, "table_name")
         self.assertIsNone(table_only.args.get("db"))
         self.assertIsNone(table_only.args.get("catalog"))
+
         db_and_table = exp.to_table("db.table_name")
         self.assertEqual(db_and_table.name, "table_name")
         self.assertEqual(db_and_table.args.get("db"), exp.to_identifier("db"))
         self.assertIsNone(db_and_table.args.get("catalog"))
+
         catalog_db_and_table = exp.to_table("catalog.db.table_name")
         self.assertEqual(catalog_db_and_table.name, "table_name")
         self.assertEqual(catalog_db_and_table.args.get("db"), exp.to_identifier("db"))
         self.assertEqual(catalog_db_and_table.args.get("catalog"), exp.to_identifier("catalog"))
 
+        table_only_unsafe_identifier = exp.to_table("3e")
+        self.assertEqual(table_only_unsafe_identifier.sql(), '"3e"')
+
     def test_to_column(self):
         column_only = exp.to_column("column_name")
         self.assertEqual(column_only.name, "column_name")

tests/test_tokens.py

@@ -201,3 +201,10 @@ x"""
         self.assertEqual(len(partial_tokens), 1)
         self.assertEqual(partial_tokens[0].token_type, TokenType.VAR)
         self.assertEqual(partial_tokens[0].text, "foo")
+
+    def test_token_repr(self):
+        # Ensures both the Python and the Rust tokenizer produce a human-friendly representation
+        self.assertEqual(
+            repr(Tokenizer().tokenize("foo")),
+            "[<Token token_type: TokenType.VAR, text: foo, line: 1, col: 3, start: 0, end: 2, comments: []>]",
+        )