pdfgen-juanipis 0.1.3__py3-none-any.whl

pdfgen/validator.py

@@ -0,0 +1,247 @@
+import copy
+import json
+import pathlib
+import re
+from typing import Any, Dict, List, Tuple
+
+
+ALLOWED_BLOCK_TYPES = {"text", "table", "figure", "map_grid", "html"}
+DEFAULT_TABLE_WIDTH = 532.66
+DEFAULT_DEP_WIDTH = 120.0
+
+
+def validate_and_normalize(data: Dict[str, Any], root_dir: pathlib.Path) -> Tuple[Dict[str, Any], List[str]]:
+    warnings: List[str] = []
+    normalized = copy.deepcopy(data)
+
+    schema_warnings = _validate_schema(normalized, root_dir)
+    warnings.extend(schema_warnings)
+
+    theme = normalized.setdefault("theme", {})
+    theme.setdefault("footer_site", "")
+    theme.setdefault("footer_phone", "")
+    theme.setdefault("show_header_titles", False)
+
+    assets_dir = root_dir / "assets"
+
+    refs_catalog = normalized.get("refs_catalog", {})
+    if refs_catalog and not isinstance(refs_catalog, dict):
+        warnings.append("refs_catalog must be a dict; ignoring invalid value")
+        refs_catalog = {}
+        normalized["refs_catalog"] = refs_catalog
+
+    if "pages" in normalized:
+        _validate_pages(normalized, assets_dir, refs_catalog, warnings)
+    elif "sections" in normalized:
+        _validate_sections(normalized, assets_dir, refs_catalog, warnings)
+    else:
+        warnings.append("data must include 'sections' or 'pages'")
+
+    return normalized, warnings
+
+
+def _validate_pages(
+    data: Dict[str, Any],
+    assets_dir: pathlib.Path,
+    refs_catalog: Dict[str, str],
+    warnings: List[str],
+) -> None:
+    pages = data.get("pages", [])
+    if not isinstance(pages, list):
+        warnings.append("pages must be a list")
+        return
+
+    for page in pages:
+        page.setdefault("refs_catalog", refs_catalog)
+        _normalize_theme_paths(page, assets_dir, warnings)
+        _validate_blocks(page.get("blocks", []), assets_dir, refs_catalog, warnings)
+
+
+def _validate_sections(
+    data: Dict[str, Any],
+    assets_dir: pathlib.Path,
+    refs_catalog: Dict[str, str],
+    warnings: List[str],
+) -> None:
+    sections = data.get("sections", [])
+    if not isinstance(sections, list):
+        warnings.append("sections must be a list")
+        return
+
+    _normalize_theme_paths(data.get("theme", {}), assets_dir, warnings)
+
+    for section in sections:
+        _validate_blocks(section.get("content", []), assets_dir, refs_catalog, warnings)
+
+
+def _validate_blocks(
+    blocks: List[Dict[str, Any]],
+    assets_dir: pathlib.Path,
+    refs_catalog: Dict[str, str],
+    warnings: List[str],
+) -> None:
+    if not isinstance(blocks, list):
+        warnings.append("blocks/content must be a list")
+        return
+
+    for block in blocks:
+        block_type = block.get("type", "text")
+        if block_type not in ALLOWED_BLOCK_TYPES:
+            warnings.append(f"Unknown block type: {block_type}")
+            continue
+
+        if block_type == "table":
+            _validate_table(block.get("table", {}), warnings)
+        elif block_type == "figure":
+            _normalize_path(block, "path", assets_dir, warnings)
+        elif block_type == "map_grid":
+            items = block.get("items", [])
+            if not isinstance(items, list):
+                warnings.append("map_grid.items must be a list")
+            else:
+                for item in items:
+                    _normalize_path(item, "path", assets_dir, warnings)
+        elif block_type == "text":
+            _validate_text_block(block, refs_catalog, warnings)
+        elif block_type == "html":
+            _warn_missing_refs(block.get("html", ""), refs_catalog, warnings)
+
+
+def _validate_table(table: Dict[str, Any], warnings: List[str]) -> None:
+    groups = table.get("groups", [])
+    rows = table.get("rows", [])
+
+    if not groups:
+        warnings.append("table.groups is empty")
+    if not rows:
+        warnings.append("table.rows is empty")
+
+    table.setdefault("total_width", DEFAULT_TABLE_WIDTH)
+    table.setdefault("dep_width", DEFAULT_DEP_WIDTH)
+
+    num_cols = 0
+    for group in groups:
+        months = group.get("months", [])
+        if not months:
+            warnings.append("table group has empty months")
+        num_cols += len(months)
+
+    if num_cols == 0:
+        return
+
+    for row in rows:
+        vals = row.get("vals", [])
+        if not isinstance(vals, list):
+            warnings.append("table row vals must be a list")
+            row["vals"] = []
+            vals = row["vals"]
+        if len(vals) < num_cols:
+            warnings.append(
+                f"table row '{row.get('dep', '')}' has {len(vals)} vals; expected {num_cols}. Padding."
+            )
+            row["vals"] = vals + [""] * (num_cols - len(vals))
+        elif len(vals) > num_cols:
+            warnings.append(
+                f"table row '{row.get('dep', '')}' has {len(vals)} vals; expected {num_cols}. Truncating."
+            )
+            row["vals"] = vals[:num_cols]
+
+
+def _validate_text_block(block: Dict[str, Any], refs_catalog: Dict[str, str], warnings: List[str]) -> None:
+    text = block.get("text", "")
+    if isinstance(text, list):
+        for paragraph in text:
+            _warn_missing_refs(paragraph, refs_catalog, warnings)
+    else:
+        _warn_missing_refs(text, refs_catalog, warnings)
+
+
+def _warn_missing_refs(text: str, refs_catalog: Dict[str, str], warnings: List[str]) -> None:
+    if not refs_catalog or not text:
+        return
+    for ref_id in _extract_ref_ids(str(text)):
+        if ref_id not in refs_catalog:
+            warnings.append(f"Missing refs_catalog entry for [{ref_id}]")
+
+
+def _normalize_theme_paths(theme: Dict[str, Any], assets_dir: pathlib.Path, warnings: List[str]) -> None:
+    _normalize_path(theme, "header_banner_path", assets_dir, warnings)
+    _normalize_path(theme, "header_banner_path_cont", assets_dir, warnings)
+    _normalize_path(theme, "header_logo_path", assets_dir, warnings)
+
+
+def _normalize_path(container: Dict[str, Any], key: str, assets_dir: pathlib.Path, warnings: List[str]) -> None:
+    if key not in container:
+        return
+    value = container.get(key)
+    if not value:
+        return
+    path = pathlib.Path(str(value))
+    if path.is_absolute():
+        return
+    candidate = assets_dir / path
+    if candidate.exists():
+        container[key] = str(candidate.resolve())
+        return
+
+    package_assets = pathlib.Path(__file__).resolve().parent / "assets"
+    candidate = package_assets / path
+    if candidate.exists():
+        container[key] = str(candidate.resolve())
+    else:
+        warnings.append(f"Asset not found for {key}: {value}")
+
+
+def _extract_ref_ids(text: str) -> List[str]:
+    ids: List[str] = []
+    seen = set()
+    for match in re.findall(r"\[(.*?)\]", text):
+        for token in re.split(r"[;,]\s*", match.strip()):
+            token = token.strip()
+            if not token:
+                continue
+            range_match = re.match(r"^(\d+)\s*[-–]\s*(\d+)$", token)
+            if range_match:
+                start = int(range_match.group(1))
+                end = int(range_match.group(2))
+                step = 1 if end >= start else -1
+                for val in range(start, end + step, step):
+                    key = str(val)
+                    if key not in seen:
+                        ids.append(key)
+                        seen.add(key)
+                continue
+            if re.match(r"^\d+$", token):
+                if token not in seen:
+                    ids.append(token)
+                    seen.add(token)
+    return ids
+
+
+def _validate_schema(data: Dict[str, Any], root_dir: pathlib.Path) -> List[str]:
+    warnings: List[str] = []
+    schema_path = root_dir / "src" / "pdfgen" / "schema.json"
+    if not schema_path.exists():
+        schema_path = pathlib.Path(__file__).resolve().parent / "schema.json"
+    if not schema_path.exists():
+        warnings.append("schema.json not found; skipping schema validation")
+        return warnings
+    try:
+        from jsonschema import Draft7Validator
+    except Exception:
+        warnings.append("jsonschema not installed; skipping schema validation")
+        return warnings
+
+    try:
+        schema = json.loads(schema_path.read_text(encoding="utf-8"))
+    except Exception as exc:
+        warnings.append(f"Failed to read schema.json: {exc}")
+        return warnings
+
+    validator = Draft7Validator(schema)
+    errors = sorted(validator.iter_errors(data), key=lambda e: e.path)
+    for err in errors:
+        loc = ".".join(str(p) for p in err.path)
+        prefix = f"schema:{loc}" if loc else "schema"
+        warnings.append(f"{prefix}: {err.message}")
+    return warnings

pdfgen_juanipis-0.1.3.dist-info/METADATA

@@ -0,0 +1,170 @@
+Metadata-Version: 2.4
+Name: pdfgen-juanipis
+Version: 0.1.3
+Summary: HTML-to-PDF generator with pagination and validation
+Author-email: Juan Pablo Díaz Correa <juanipis@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/Juanipis/pdfgen-juanipis
+Project-URL: Issues, https://github.com/Juanipis/pdfgen-juanipis/issues
+Project-URL: Source, https://github.com/Juanipis/pdfgen-juanipis
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: Jinja2==3.1.4
+Requires-Dist: WeasyPrint==59.0
+Requires-Dist: pydyf==0.10.0
+Requires-Dist: jsonschema==4.23.0
+Requires-Dist: PyYAML==6.0.2
+Dynamic: license-file
+
+# pdfgen
+
+Librería para generar PDFs a partir de data estructurada (HTML + WeasyPrint), con paginación, validación y soporte JSON/YAML.
+
+## Instalación
+
+Desde el repo:
+
+```bash
+pip install -e .
+```
+
+## Uso básico (Python)
+
+```python
+from pdfgen.api import PDFGenConfig, PDFGen
+
+config = PDFGenConfig.from_root("/ruta/a/tu/proyecto")
+pdf = PDFGen(config)
+
+pdf.render(data, output_path="salida.pdf", paginate=True, validate=True)
+```
+
+Atajo:
+
+```python
+from pdfgen.api import render_with_defaults
+
+render_with_defaults(data, output_path="salida.pdf", root_dir="/ruta/a/tu/proyecto")
+```
+
+## CLI
+
+Render (JSON o YAML):
+
+```bash
+pdfgen render data.json salida.pdf --root /ruta/proyecto
+pdfgen render data.yaml salida.pdf
+```
+
+Validar (sin generar PDF):
+
+```bash
+pdfgen validate data.yaml
+```
+
+Desde stdin (YAML por defecto):
+
+```bash
+cat data.yaml | pdfgen render - salida.pdf
+```
+
+Opciones útiles:
+- `--template-dir` usar tu template
+- `--css` usar tu CSS
+- `--fonts-conf` usar un `fonts.conf` propio
+- `--fonts-dir` usar un directorio con `.ttf`
+- `--css-extra` inyectar CSS adicional
+- `--no-validate` desactivar validación
+- `--no-paginate` desactivar paginación
+
+## Personalización
+
+### Fuentes propias
+
+Opción A: `fonts.conf` propio.
+
+```python
+config = PDFGenConfig.from_root("/ruta/a/tu/proyecto")
+config.fonts_conf = "/ruta/a/mi/fonts.conf"
+PDFGen(config).render(data, "salida.pdf")
+```
+
+Opción B: directorio con `.ttf` desde CLI:
+
+```bash
+pdfgen render data.json salida.pdf --fonts-dir /ruta/a/mis/fuentes
+```
+
+### Colores/estilos rápidos
+
+Puedes inyectar CSS extra para cambiar variables o estilos:
+
+```python
+css_extra = ":root { --blue-title: #0b7285; --orange-footer: #f08c00; }"
+render_with_defaults(data, "salida.pdf", root_dir="/ruta", css_extra=css_extra)
+```
+
+### Template y CSS propios
+
+```bash
+pdfgen render data.json salida.pdf --template-dir /ruta/template --css /ruta/template/boletin.css
+```
+
+## Estructura mínima del data
+
+```python
+data = {
+  "theme": {
+    "header_banner_path": "banner.png",
+    "header_logo_path": "logo.png",
+    "title_line1": "Titulo",
+    "title_line2": "Subtitulo",
+    "footer_site": "example.org",
+    "footer_phone": "Contacto: +1 555 0100"
+  },
+  "sections": [
+    {
+      "title": "I. Introduccion",
+      "content": [
+        {"type": "text", "text": "Texto con <strong>negrita</strong>."}
+      ]
+    }
+  ]
+}
+```
+
+## Estilos inline
+
+Los bloques de texto aceptan HTML:
+- `<strong>` negrita
+- `<em>` itálica
+- `<u>` subrayado
+- `<s>` tachado
+
+## Ejemplos
+
+- `examples/minimal.yaml`
+
+## Validación
+
+Se valida automáticamente con `schema.json`. Los warnings se imprimen en consola.
+
+Si quieres desactivar:
+
+```python
+pdf.render(data, output_path="salida.pdf", validate=False)
+```
+
+## Licencia
+
+MIT
+
+## Releases
+
+Al hacer push a `main`, el workflow **Auto Release** crea tag y Release si la versión en `pyproject.toml` es nueva, y publica automáticamente en PyPI.
+
+
+Hecho por Juanipis

pdfgen_juanipis-0.1.3.dist-info/RECORD

@@ -0,0 +1,33 @@
+pdfgen/__init__.py,sha256=4jtt7D6NgNMRk-UO_UXrtn17gjir-RDulcptgOmp56Y,446
+pdfgen/api.py,sha256=d9cJ-Seu9EwgIqCeityHgchsMUWcaczwd554njSkISM,2051
+pdfgen/cli.py,sha256=QTWF6-xYG7IE61vj39P59rlLu9ValcZtGsxmFd9GO4I,3782
+pdfgen/pagination.py,sha256=8A-mtFM_tMOUH5jZT7fojpItxDGu1vSUIVmcAOT1Ezk,39027
+pdfgen/render.py,sha256=qUqfhUFFAks76rjicgmC3MQqfelde-KF7Ewri4nyfx4,14895
+pdfgen/schema.json,sha256=vzpefhYtHW7cQj9zQaPmgBYSr6JvsYK45XB5PoISVu4,3863
+pdfgen/validator.py,sha256=FmnMZjb-CcZeyTicJlevigk8awXd0tMFkRFa85HSPt8,8510
+pdfgen/assets/banner-clean.png,sha256=mNJeBFUS1EPWYPN74u_1nHLl7moerw-NmkvYuzUuFzo,1023
+pdfgen/assets/banner.png,sha256=0qvxaK2MTvRF7zk_vqzkge_zUPWr9BU8NdFFLdhH5uo,1543
+pdfgen/assets/logo.png,sha256=mdlP4nHd67W5iaaIJetBLNWbbchkcMe7X0FrbiIw34A,1124
+pdfgen/assets/fonts/BCDEEE_Calibri_5.ttf,sha256=p_g3mkSqeuHzYku1RQeJbB0u4ObVLFrFXw9OK8jBKdc,166944
+pdfgen/assets/fonts/BCDFEE_CenturyGothic-Bold_9.ttf,sha256=nnSa8BTxjLyjHKPvwWIcKj0n-1v7GPyx1hFm7wzpIc0,25004
+pdfgen/assets/fonts/BCDGEE_CenturyGothic-Bold_14.ttf,sha256=nnSa8BTxjLyjHKPvwWIcKj0n-1v7GPyx1hFm7wzpIc0,25004
+pdfgen/assets/fonts/BCDHEE_Calibri-Bold_20.ttf,sha256=fucZ-DSOZKk1zeOR1SRpXpXvTiUz43x94ng4jMWbtE4,123256
+pdfgen/assets/fonts/BCDIEE_Calibri-Bold_25.ttf,sha256=fucZ-DSOZKk1zeOR1SRpXpXvTiUz43x94ng4jMWbtE4,123256
+pdfgen/assets/fonts/BCDJEE_Calibri_27.ttf,sha256=p_g3mkSqeuHzYku1RQeJbB0u4ObVLFrFXw9OK8jBKdc,166944
+pdfgen/assets/fonts/BCDKEE_Calibri-Italic_33.ttf,sha256=RLWG91jghcpaYURNRQUlaMaUZdbGKaLa037peB1PbaM,117848
+pdfgen/assets/fonts/BCDLEE_Calibri-Italic_52.ttf,sha256=RLWG91jghcpaYURNRQUlaMaUZdbGKaLa037peB1PbaM,117848
+pdfgen/assets/fonts/BCDMEE_SegoeUI_54.ttf,sha256=w0Ksdnsp8yvwx8LwzybaBX6NuITVJWS8l0XTm9-xQtc,68880
+pdfgen/assets/fonts/BCDNEE_SegoeUI_60.ttf,sha256=w0Ksdnsp8yvwx8LwzybaBX6NuITVJWS8l0XTm9-xQtc,68880
+"pdfgen/assets/fonts/BCDOEE_Aptos Narrow,Bold_142.ttf",sha256=hrK2c59rBQ4lkX9_-nFHbBMfoDikd9M47hRxiMw3at8,23896
+"pdfgen/assets/fonts/BCDPEE_Aptos Narrow,Bold_144.ttf",sha256=hrK2c59rBQ4lkX9_-nFHbBMfoDikd9M47hRxiMw3at8,23896
+pdfgen/assets/fonts/BCEAEE_Aptos Narrow_149.ttf,sha256=mg-JKL3wHgRd_qVRAXXn6IKGnl_PJZnx5j95WAl6VB8,30924
+pdfgen/assets/fonts/BCEBEE_Aptos Narrow_154.ttf,sha256=mg-JKL3wHgRd_qVRAXXn6IKGnl_PJZnx5j95WAl6VB8,30924
+pdfgen/assets/fonts/TimesNewRomanPS-BoldMT_38.ttf,sha256=CAyIzST1vKiE9DhZriELQ_OzNeBrnWFQmAdRu4Qdoz0,90100
+pdfgen/templates/boletin.css,sha256=lCiCNkCcHrUepmm3JnnbQxSf_UZBYCqGBiIYFXlk2t8,6244
+pdfgen/templates/boletin_template.html.jinja,sha256=aWdeFc-1VkynxGSe4WaL3SqkEKLOQz63K28SMmQ_qOI,4550
+pdfgen_juanipis-0.1.3.dist-info/licenses/LICENSE,sha256=ESYyLizI0WWtxMeS7rGVcX3ivMezm-HOd5WdeOh-9oU,1056
+pdfgen_juanipis-0.1.3.dist-info/METADATA,sha256=jjHPP5RK_WOpVw8HPkuBjOOrEwXZaFT4yIh6cIeUdOg,3718
+pdfgen_juanipis-0.1.3.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+pdfgen_juanipis-0.1.3.dist-info/entry_points.txt,sha256=k94J3IsuMlLw09pyLYkVqXq3rhbUusR_oblgNBD8Qfk,43
+pdfgen_juanipis-0.1.3.dist-info/top_level.txt,sha256=j-KjOvwSSJxIWLnr7bjvZj2JiCMp-_DCKA0rGQl89e4,7
+pdfgen_juanipis-0.1.3.dist-info/RECORD,,

pdfgen_juanipis-0.1.3.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.10.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

pdfgen_juanipis-0.1.3.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+pdfgen = pdfgen.cli:main

pdfgen_juanipis-0.1.3.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

pdfgen_juanipis-0.1.3.dist-info/top_level.txt

@@ -0,0 +1 @@
+pdfgen