Metadata-Version: 2.4
Name: pyxsql
Version: 1.2.0
Summary: SQL-style querying for static HTML with a deterministic node model.
Author: BORANN CHANRATHNAK
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
           any Contribution intentionally submitted for inclusion in the Work
           by You to the Licensor shall be under the terms and conditions of
           this License, without any additional terms or conditions.
           Notwithstanding the above, nothing herein shall supersede or modify
           the terms of any separate license agreement you may have executed
           with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
           names, trademarks, service marks, or product names of the Licensor,
           except as required for reasonable and customary use in describing the
           origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
           agreed to in writing, Licensor provides the Work (and each
           Contributor provides its Contributions) on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
           implied, including, without limitation, any warranties or conditions
           of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
           PARTICULAR PURPOSE. You are solely responsible for determining the
           appropriateness of using or redistributing the Work and assume any
           risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
           whether in tort (including negligence), contract, or otherwise,
           unless required by applicable law (such as deliberate and grossly
           negligent acts) or agreed to in writing, shall any Contributor be
           liable to You for damages, including any direct, indirect, special,
           incidental, or consequential damages of any character arising as a
           result of this License or out of the use or inability to use the
           Work (including but not limited to damages for loss of goodwill,
           work stoppage, computer failure or malfunction, or any and all
           other commercial damages or losses), even if such Contributor
           has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
           the Work or Derivative Works thereof, You may choose to offer,
           and charge a fee for, acceptance of support, warranty, indemnity,
           or other liability obligations and/or rights consistent with this
           License. However, in accepting such obligations, You may act only
           on Your own behalf and on Your sole responsibility, not on behalf
           of any other Contributor, and only if You agree to indemnify,
           defend, and hold each Contributor harmless for any liability
           incurred by, or claims asserted against, such Contributor by reason
           of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           Copyright 2025 BORANN CHANRATHNAK
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
        
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: C++
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: test
Requires-Dist: pytest>=7.4.0; extra == "test"
Dynamic: license-file

# XSQL Documentation (v1.2.0)

XSQL is a SQL-style query language for static HTML. It treats each HTML element
as a row in a node table and lets you filter by tag, attributes, and position.
The project is now at v1.2.0 as an offline-first C++20 tool.

## Quick Start

Build:
```
./build.sh
```

Run on a file:
```
./build/xsql --query "SELECT a FROM doc WHERE attributes.id = 'login'" --input ./data/index.html
```

Interactive mode:
```
./build/xsql --interactive --input ./data/index.html
```

## Python API (xsql package)

```python
import xsql

doc = xsql.load("data/index.html")
print(xsql.summarize(doc))
rows = xsql.execute("SELECT a FROM document WHERE attributes.href IS NOT NULL")

doc = xsql.load("https://example.com", allow_network=True)
rows = xsql.execute("SELECT title FROM document")
```

Install:
```
pip install pyxsql
```

Security Notes:
- Network access is disabled by default; enable with `allow_network=True`.
- Private/localhost targets are blocked unless `allow_private_network=True`.
- File reads are confined to `base_dir` when provided.
- Downloads are capped by `max_bytes`, and query output by `max_results`.

## Build on Linux/macOS/Windows

Linux (Ubuntu/Debian):
```
sudo apt-get update
sudo apt-get install -y build-essential cmake ninja-build pkg-config bison flex
./build.sh
```

macOS (Homebrew):
```
brew install cmake ninja pkg-config bison flex
./build.sh
```

Windows (PowerShell, MSVC):
```
cmake -S . -B build -DCMAKE_TOOLCHAIN_FILE=C:\vcpkg\scripts\buildsystems\vcpkg.cmake -DVCPKG_TARGET_TRIPLET=x64-windows
cmake --build build --config Release
```

Optional dependencies via vcpkg:
```
vcpkg install nlohmann-json libxml2 curl arrow[parquet]
```

If you do not want Parquet, configure with `-DXSQL_WITH_ARROW=OFF`.

## Python Build & Tests

Create a virtual environment and install the editable package:
```
python3 -m venv xsql_venv
source ./xsql_venv/bin/activate
pip install -U pip
pip install -e .[test]
```

Run Python tests:
```
pytest -v python/tests
```

Shorthand:
```
./install_python.sh
./test_python.sh
```

## CLI Usage

```
./build/xsql --query "<query>" --input <path>
./build/xsql --query-file <file> --input <path>
./build/xsql --interactive [--input <path>]
./build/xsql --mode duckbox|json|plain
./build/xsql --display_mode more|less
./build/xsql --highlight on|off
./build/xsql --color=disabled
```

Notes:
- `--input` is required unless reading HTML from stdin.
- Colors are auto-disabled when stdout is not a TTY.
- Default output mode is `duckbox` (table-style).
- `--highlight` only affects duckbox headers (auto-disabled when not a TTY).
- `--display_mode more` disables JSON truncation in non-interactive mode.
- `TO CSV()` / `TO PARQUET()` write files instead of printing results.

## Interactive Mode (REPL)

Commands:
- `.help`: show help
- `.load <path|url>` / `:load <path|url>`: load input (path or URL)
- `.mode duckbox|json|plain`: set output mode
- `.display_mode more|less`: control JSON truncation
- `.max_rows <n|inf>`: set duckbox max rows (`inf` = unlimited)
- `.summarize [doc|path|url]`: list all tags and counts for the active input or target
- `.quit` / `.q` / `:quit` / `:exit`: exit the REPL

Keys:
- Up/Down: history (max 5 entries)
- Left/Right: move cursor
- Ctrl+L: clear screen

## Data Model

Each HTML element becomes a row with fields:
- `node_id` (int64)
- `tag` (string)
- `attributes` (map<string,string>)
- `parent_id` (int64 or null)
- `sibling_pos` (int64, 1-based position among siblings)
- `source_uri` (string)

## Query Language

### Basic Form
```
SELECT <tag_list> FROM <source> [WHERE <expr>] [LIMIT <n>]
  [TO LIST() | TO TABLE([HEADER=ON|OFF][, EXPORT='file.csv']) | TO CSV('file.csv') | TO PARQUET('file.parquet')]
```

### Source
```
FROM document
FROM 'path.html'
FROM 'https://example.com'   (URL fetching requires libcurl)
FROM RAW('<div class="card"></div>')
FROM FRAGMENTS(RAW('<ul><li>1</li><li>2</li></ul>')) AS frag
FROM FRAGMENTS(SELECT inner_html(div) FROM doc WHERE attributes.class = 'pagination') AS frag
FROM doc                     (alias for document)
FROM document AS doc
```

Notes:
- `RAW('<html>')` parses an inline HTML string as the document source.
- `FRAGMENTS(...)` builds a temporary document by concatenating HTML fragments.
- `FRAGMENTS` accepts either `RAW('<html>')` or a subquery returning a single HTML string column (use `inner_html(...)`).
- `FRAGMENTS` subqueries cannot use file or URL sources.

### Tags
```
SELECT div
SELECT div,span
SELECT *
```

Exclude columns:
```
SELECT * EXCLUDE source_uri FROM doc
SELECT * EXCLUDE (source_uri, tag) FROM doc
```

### WHERE Expressions
Supported operators:
- `=`
- `IN`
- `<>` / `!=`
- `IS NULL` / `IS NOT NULL`
- `~` (regex, ECMAScript)
- `CONTAINS` (attributes only, case-insensitive)
- `HAS_DIRECT_TEXT` (case-insensitive substring match on direct text)
- `AND`, `OR`

Attribute references:
```
attributes.id = 'main'
parent.attributes.class = 'menu'
child.attributes.href <> ''
ancestor.attributes.id = 'root'
descendant.attributes.class IN ('nav','top')
attributes.href CONTAINS 'example'
```

Field references:
```
text <> ''
tag = 'div'
parent.tag = 'section'
child.tag = 'a'
ancestor.text ~ 'error|warning'
div HAS_DIRECT_TEXT 'login'
sibling_pos = 2
```

Shorthand attribute filters:
```
title = "Menu"
doc.title = "Menu"
```

### Aliases
Alias the source and qualify attribute filters:
```
SELECT a FROM document AS d WHERE d.attributes.id = 'login'
```

### Projections
Project a field from a tag:
```
SELECT a.parent_id FROM doc
SELECT link.href FROM doc
SELECT a.attributes FROM doc
SELECT div(node_id, tag, parent_id) FROM doc
```

Supported base fields:
- `node_id`, `tag`, `parent_id`, `sibling_pos`, `source_uri`, `attributes`

Attribute value projection:
- `SELECT link.href FROM doc` returns the `href` value

Function projection:
- `SELECT inner_html(div) FROM doc` returns the raw inner HTML for each `div`
- `SELECT inner_html(div, 1) FROM doc` keeps only tags up to depth 1 (drops deeper tags)
- `SELECT trim(inner_html(div)) FROM doc` trims leading/trailing whitespace
- `SELECT TEXT(div) FROM doc WHERE tag = 'div'` returns descendant text for each `div`

Notes:
- `TEXT()` and `INNER_HTML()` require a `WHERE` clause with a non-tag filter (e.g., attributes or parent).
- `attributes IS NULL` matches elements with no attributes.

### TO LIST()
Output a JSON list for a single projected column:
```
SELECT link.href FROM doc WHERE attributes.rel = "preload" TO LIST()
```

### TO TABLE()
Extract an HTML `<table>` into rows (array of arrays). By default the first row
is treated as column headers for duckbox rendering; set `HEADER=OFF` to render
all rows as data (CSV exports will include generated `col1..colN` headers):
```
SELECT table FROM doc TO TABLE()
SELECT table FROM doc TO TABLE(HEADER=OFF)
SELECT table FROM doc WHERE attributes.id = 'stats' TO TABLE(EXPORT='stats.csv')
```

If multiple tables match, the output is a list of objects:
```
[{ "node_id": 123, "rows": [[...], ...] }, ...]
```

Note: `TO LIST()` always returns JSON output. `TO TABLE()` uses duckbox by default and JSON in `--mode json|plain`.
`EXPORT='file.csv'` requires a single table result, so filter by `node_id` or attributes when multiple tables match.

### TO CSV()
Write any rectangular result to a CSV file:
```
SELECT a.href, a.text FROM doc WHERE attributes.href IS NOT NULL TO CSV('links.csv')
```

### TO PARQUET()
Write any rectangular result to a Parquet file (requires Apache Arrow feature):
```
SELECT * FROM doc TO PARQUET('nodes.parquet')
```

Note: `TO CSV()` and `TO PARQUET()` write files and do not print the result set.
If you `SELECT table ... TO CSV(...)`, XSQL exports the HTML table rows directly (legacy).
Prefer `TO TABLE(EXPORT='file.csv')` for explicit table exports.

### LIMIT
```
SELECT a FROM doc LIMIT 5
```

### COUNT()
Minimal aggregate:
```
SELECT COUNT(a) FROM doc
SELECT COUNT(*) FROM doc
SELECT COUNT(link) FROM doc WHERE attributes.rel = "preload"
```

### Regex
Use `~` with ECMAScript regex:
```
SELECT a FROM doc WHERE attributes.href ~ '.*\\.pdf$'
```

### Contains (attributes)
Case-insensitive substring match for attribute values:
```
SELECT a FROM doc WHERE attributes.href CONTAINS 'techkhmer'
SELECT a FROM doc WHERE attributes.href CONTAINS ALL ('https', '.html')
SELECT a FROM doc WHERE attributes.href CONTAINS ANY ('https', 'mailto')
```

### Direct Text
Case-insensitive substring match on direct text only (excluding nested tags):
```
SELECT div FROM doc WHERE div HAS_DIRECT_TEXT 'computer science'
```

### TFIDF()
Compute per-node TF-IDF scores across the matched nodes. Each matched node is
treated as a document in the IDF corpus.
```
SELECT TFIDF(p, li, TOP_TERMS=30, MIN_DF=1, MAX_DF=0, STOPWORDS=ENGLISH)
  FROM doc WHERE attributes.class = 'article'
```

Output columns: `node_id`, `parent_id`, `tag`, `terms_score` (term → score map).

Options:
- `TOP_TERMS` (default 30): max terms per node.
- `MIN_DF` (default 1): minimum document frequency.
- `MAX_DF` (default 0 = no max): maximum document frequency.
- `STOPWORDS` (`ENGLISH` or `NONE`, default `ENGLISH`).

Notes:
- Tags must come before options inside `TFIDF(...)`.
- TFIDF is an aggregate and must be the only select item.
- TFIDF ignores HTML tags and skips script/style/noscript content.

## Examples

```
-- Filters
SELECT ul FROM doc WHERE attributes.id = 'countries';
SELECT table FROM doc WHERE parent.attributes.id = 'table-01';
SELECT div FROM doc WHERE descendant.attributes.class = 'card';
SELECT span FROM doc WHERE parent_id = 1;
SELECT span FROM doc WHERE node_id = 1;
SELECT div FROM doc WHERE attributes IS NULL;

-- Lists and exports
SELECT link.href FROM doc WHERE attributes.rel = "preload" TO LIST();
SELECT a.href, a.text FROM doc WHERE attributes.href IS NOT NULL TO CSV('links.csv');
SELECT * FROM doc TO PARQUET('nodes.parquet');

-- Fragments
SELECT li FROM FRAGMENTS(SELECT inner_html(ul) FROM doc WHERE attributes.id = 'menu') AS frag;

-- Ordering
SELECT div FROM doc ORDER BY node_id DESC;
SELECT * FROM doc ORDER BY tag, parent_id LIMIT 10;

-- Summaries
SELECT summarize(*) FROM doc;
SELECT summarize(*) FROM doc ORDER BY count DESC LIMIT 5;
```

## TODO

| Item | Priority |
| --- | --- |
| DOM mutation: `UPDATE` / `INSERT` / `DELETE` | High |
| DOM mutation: attribute ops (`SET`, `REMOVE`) | High |
| DOM mutation: content ops (`SET TEXT`, `SET INNER_HTML`) | High |
| DB bridge: `TO DB()` / `FROM DB()` (XSQL stays front-end) | High |
| Multi-source `JOIN` (doc ↔ doc, doc ↔ table) | Medium |
| `WITH` / subqueries for reuse | Medium |
| `GROUP BY` + `HAVING` + `DISTINCT` | Medium |
| Performance profiling + hot-path optimizations | Medium |
| Session cache for parsed DOM (if a clear use case appears) | Low |
| BM25 ranking (simple explainer on demand) | Exploration |

## Known Limitations

- No XPath or positional predicates.
- `ORDER BY` is limited to `node_id`, `tag`, `text`, or `parent_id`.
- No `GROUP BY` or joins.
- No XML mode (HTML only).
- URL fetching requires libcurl.
- Default output is duckbox tables; JSON output is available via `--mode json`.
- `TO PARQUET()` requires Apache Arrow support at build time.

## Build Dependencies

Optional:
- `nlohmann/json` for pretty JSON output (vcpkg recommended).
- `libxml2` for robust HTML parsing (fallback to naive parser if missing).
- `libcurl` for URL fetching.
- `apache-arrow` (Arrow/Parquet) for `TO PARQUET()` export.

## Troubleshooting

- If you see `No input loaded` in REPL, run `:load <path|url>`.
- If a query fails with `Expected FROM`, include a `FROM` clause.
- If output is compact JSON, ensure `nlohmann/json` is linked via vcpkg.
