pdfpainter 0.1.0__tar.gz

pdfpainter-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   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.

pdfpainter-0.1.0/NOTICE

@@ -0,0 +1,7 @@
+pdfpainter
+Copyright 2026 Vaibhav Rawat (AdRaw App Studio)
+
+This product is licensed under the Apache License, Version 2.0 (see LICENSE).
+It paints PDF pages to images with Pillow alone.
+
+Originally developed as part of docextract by AdRaw App Studio.

pdfpainter-0.1.0/PKG-INFO

@@ -0,0 +1,312 @@
+Metadata-Version: 2.4
+Name: pdfpainter
+Version: 0.1.0
+Summary: Paint PDF pages to images with Pillow alone: no native PDF engine, permissive licence, exact text positions. For OCR and page previews where PDF DLLs can't run.
+Author: Vaibhav Rawat (AdRaw App Studio)
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/Vibhu1712/pdfpainter
+Project-URL: Issues, https://github.com/Vibhu1712/pdfpainter/issues
+Project-URL: Changelog, https://github.com/Vibhu1712/pdfpainter/blob/main/CHANGELOG.md
+Keywords: pdf,render,rasterize,pdf to image,pillow,ocr,pure python
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Multimedia :: Graphics :: Graphics Conversion
+Classifier: Topic :: Office/Business
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+License-File: THIRD_PARTY_NOTICES.md
+Requires-Dist: pdfsieve>=0.1.0
+Requires-Dist: pdfminer.six>=20240706
+Requires-Dist: Pillow>=9.1
+Requires-Dist: numpy>=1.21
+Provides-Extra: test
+Requires-Dist: pytest>=7; extra == "test"
+Requires-Dist: reportlab>=4; python_version >= "3.10" and extra == "test"
+Requires-Dist: reportlab<=4.5.0,>=4; python_version < "3.10" and extra == "test"
+Dynamic: license-file
+
+# pdfpainter
+
+**Paint PDF pages to images with Pillow alone: no native PDF engine, Apache-2.0 licensed, text in exactly the right place.**
+
+```python
+import pdfpainter
+
+img = pdfpainter.render_pdf("payslip.pdf", page=0, dpi=150)   # a Pillow image
+img.save("payslip-1.png")
+```
+
+![The same payslip painted by PDFium and by pdfpainter](docs/comparison.png)
+
+## Why pdfpainter
+
+Most ways to turn a PDF page into an image load a native engine: MuPDF, PDFium, Poppler or Ghostscript. That fails where policies block unsigned DLLs (Windows Application Control on government and bank PCs, locked-down servers), and some of those engines are AGPL or GPL.
+
+pdfpainter paints pages with **Pillow and NumPy only**, from what [pdfsieve](https://github.com/Vibhu1712/pdfsieve) reads with pure-Python pdfminer.six. It is built for two jobs:
+
+1. **OCR** of pages with no usable text layer: scans, and text drawn as outlines (for example PDFs from "Microsoft Print to PDF"). Letter outlines are filled with their holes, so OCR  reads them.
+2. **Showing a page on screen** so users can see it, click on it, or drag boxes over it. Words land in exactly the positions the PDF gives them.
+
+It is **not** a full PDF renderer; see [what is drawn](#what-is-drawn-and-what-isnt). For pixel-perfect output, use PDFium (pypdfium2) when it's available and fall back to pdfpainter when it isn't. The two produce images of the same size, so they're interchangeable.
+
+## Contents
+
+- [Install](#install)
+- [Quick start](#quick-start)
+- [Command line](#command-line)
+- [API reference](#api-reference)
+- [Recipes](#recipes)
+- [What is drawn, and what isn't](#what-is-drawn-and-what-isnt)
+- [Fonts](#fonts)
+- [Speed](#speed)
+- [Development](#development)
+- [Licence](#licence)
+
+## Install
+
+```bash
+pip install pdfpainter
+```
+
+Python 3.9 or newer. Installs pdfsieve, pdfminer.six, Pillow and NumPy, all with permissive licences and wheels for every common platform.
+
+## Quick start
+
+```python
+import pdfpainter
+import pdfsieve
+
+# one call: open, paint, close
+img = pdfpainter.render_pdf("statement.pdf", page=0, dpi=200)
+
+# or paint pages you already opened with pdfsieve
+with pdfsieve.open("statement.pdf") as doc:
+    for page in doc:
+        img = pdfpainter.render(page, zoom=2.0)          # 2 pixels per point = 144 dpi
+        img.save(f"statement-{page.index + 1}.png")
+
+# find out what couldn't be drawn
+info = {}
+img = pdfpainter.render_pdf("scan.pdf", dpi=300, info=info)
+print(info)   # {'undecoded': 0, 'skipped_fills': 0}
+```
+
+**Zoom and dpi.** `zoom` is pixels per PDF point; `dpi = zoom × 72`. A word box from pdfsieve maps onto the image by multiplying each coordinate by `zoom`.
+
+## Command line
+
+```bash
+pdfpainter payslip.pdf                         # every page to payslip-1.png, payslip-2.png, ...
+pdfpainter payslip.pdf -o page.png -p 1        # one page
+pdfpainter payslip.pdf -o "out/p{page}.jpg"    # {page} is the page number; extension picks the format
+pdfpainter payslip.pdf --dpi 300               # default 150
+pdfpainter payslip.pdf --no-text               # shapes and images only
+pdfpainter locked.pdf --password secret
+```
+
+Each file written is listed with its size, plus a note if something on the page couldn't be shown:
+
+```
+k-1.png  (417 x 417)  note: 1 image(s) in an unsupported format shown as grey boxes
+```
+
+## API reference
+
+### `render(page, zoom=1.0, info=None, *, dpi=None, background=(255, 255, 255), text=True, antialias=True)`
+
+Paint a `pdfsieve.Page` and return an RGB `PIL.Image.Image`.
+
+| Argument | Meaning |
+|---|---|
+| `page` | A page from `pdfsieve.open(...).page(i)`. |
+| `zoom` | Pixels per point. `1.0` is 72 dpi. |
+| `dpi` | Alternative to `zoom`: dots per inch. |
+| `info` | A dict to receive `undecoded` (images in an unsupported format, drawn as grey boxes)  and `skipped_fills` (shapes filled with a pattern or shading, left out). |
+| `background` | Page colour. |
+| `text` | `False` leaves the text layer out, to see what a page looks like without it. |
+| `antialias` | Paint vector content at twice the size, then shrink, for smooth edges. Turn off for speed. |
+
+The image size is `ceil(width × zoom) × ceil(height × zoom)`, the same rounding PDFium uses
+(see `page_size_px(page, zoom)`).
+
+### `render_pdf(source, page=0, zoom=1.0, *, dpi=None, password="", info=None, **kwargs)`
+
+Open a PDF (path, bytes or binary file object), paint one page (0-based), and close it. Other
+keyword arguments go to `render`.
+
+### `decode_image(stream) -> (image or None, is_stencil)`
+
+Decode one embedded image (a pdfminer stream, e.g. `page.pictures[0].stream`) into a Pillow image,
+for extracting a scan's image without rendering the whole page. Returns `(None, False)` for
+unsupported formats.
+
+### Fonts
+
+| | |
+|---|---|
+| `add_font_dir(path)` | Search a folder for fonts before the system folders. |
+| `font_dirs()` | The folders searched, in order. |
+| `find_font(family, bold, italic=False)` | Path of the font used for `"sans"`, `"serif"`, `"mono"`, `"indic"` or `"cjk"`. |
+| `font_for(pdf_font_name, char, px)` | The Pillow font used to draw a character. |
+| `FAMILIES`, `ITALICS` | The candidate font file names per family; edit to prefer other fonts. |
+
+The `PDFPAINTER_FONT_DIRS` environment variable adds folders too (separated by `;` on Windows and
+`:` elsewhere).
+
+### Other
+
+| | |
+|---|---|
+| `page_size_px(page, zoom)` | Size in pixels `render` will produce. |
+| `to_ppm(img)` | PPM bytes that Tkinter's `PhotoImage(data=...)` shows with no extra libraries. |
+| `MAX_PIXELS` | Above this canvas size, `antialias` is skipped to save memory. |
+
+## Recipes
+
+Runnable versions live in [`examples/`](examples). Make the sample PDF with
+`python examples/make_sample_pdf.py` (needs `pip install reportlab`).
+
+### OCR a page that has no text layer
+
+```python
+import numpy as np
+import pdfpainter, pdfsieve
+from rapidocr import RapidOCR        # pip install rapidocr onnxruntime
+
+zoom = 300 / 72
+with pdfsieve.open("printed-to-pdf.pdf") as doc:
+    img = pdfpainter.render(doc.page(0), zoom)
+
+result = RapidOCR()(np.asarray(img))
+for quad, text in zip(result.boxes, result.txts):
+    xs, ys = [p[0] for p in quad], [p[1] for p in quad]
+    print(min(xs) / zoom, min(ys) / zoom, text)    # back in PDF points, like pdfsieve's words
+```
+
+[`examples/ocr_page.py`](examples/ocr_page.py) does the same with RapidOCR or, if that isn't
+installed, Tesseract.
+
+### Draw word boxes over the page
+
+```python
+from PIL import ImageDraw
+
+zoom = 2.0
+with pdfsieve.open("sample.pdf") as doc:
+    page = doc.page(0)
+    img = pdfpainter.render(page, zoom)
+    draw = ImageDraw.Draw(img)
+    for w in page.words():
+        draw.rectangle([v * zoom for v in w[:4]], outline="red", width=2)
+img.save("boxes.png")
+```
+
+### PDFium when allowed, pdfpainter when not
+
+```python
+def page_image(path, index, zoom):
+    try:
+        import pypdfium2 as pdfium
+        pdf = pdfium.PdfDocument(path)
+        try:
+            return pdf[index].render(scale=zoom).to_pil().convert("RGB")
+        finally:
+            pdf.close()
+    except Exception:                 # not installed, or its DLL is blocked
+        return pdfpainter.render_pdf(path, index, zoom)
+```
+
+### Show a page in Tkinter with no extra libraries
+
+```python
+import tkinter as tk
+
+root = tk.Tk()
+photo = tk.PhotoImage(data=pdfpainter.to_ppm(pdfpainter.render_pdf("sample.pdf", dpi=96)))
+tk.Label(root, image=photo).pack()
+root.mainloop()
+```
+
+### Pull the scanned image out of a page
+
+```python
+with pdfsieve.open("scan.pdf") as doc:
+    pic = doc.page(0).pictures[0]
+    img, is_stencil = pdfpainter.decode_image(pic.stream)
+    if img is not None:
+        img.save("scan.png")          # at the scan's own resolution
+```
+
+## What is drawn, and what isn't
+
+**Drawn**
+
+- Filled and stroked paths, with curves, line widths and colours (gray, RGB, CMYK, spot tints).
+- Holes in shapes under both fill rules, so letters drawn as outlines (`o`, `e`, `8`) keep their
+  counters and OCR reads them.
+- Embedded images, upright or rotated: JPEG, JPEG 2000 (if your Pillow reads it), and raw, Flate,
+  LZW or RunLength data in gray, RGB, CMYK, ICC, calibrated and indexed colour spaces at
+  1–16 bits; 1-bit stencil masks in the current fill colour.
+- Real text in a similar system font (sans, serif or mono, bold and italic, Indic and CJK
+  scripts), on its exact baseline, including sideways and upside-down text. Invisible text, such
+  as a scan's OCR layer, is not drawn.
+
+**Not drawn**
+
+- Clipping paths: content outside a clip still shows.
+- Transparency and blend modes: everything is opaque.
+- Pattern and shading fills (gradients): left out and counted in `info["skipped_fills"]`.
+- Dashed lines are drawn solid; line caps and joins are approximated.
+- The PDF's own embedded fonts: text is set in a system font, so letter shapes and widths differ
+  slightly, though each character starts where the PDF puts it.
+- JBIG2 images (common in scanned archives) and unusual colour spaces (DeviceN, Lab images): drawn
+  as grey boxes and counted in `info["undecoded"]`.
+- Annotations and form-field appearances.
+
+## Fonts
+
+Text is set in fonts already on the computer:
+
+| Family | Windows | macOS | Linux |
+|---|---|---|---|
+| sans | Arial, Segoe UI | Arial | Liberation Sans, DejaVu Sans, FreeSans |
+| serif | Times New Roman | Times New Roman | Liberation Serif, DejaVu Serif, FreeSerif |
+| mono | Courier New | Courier New | Liberation Mono, DejaVu Sans Mono, FreeMono |
+| indic | Nirmala UI, Mangal | Kohinoor | Noto Sans Devanagari |
+| cjk | Yu Gothic, MS Gothic, Microsoft YaHei, Malgun Gothic | PingFang | Noto Sans CJK |
+
+The family is chosen from the PDF's font name (`Times`, `Courier`, `Bold`, `Italic`, ...) and the
+character's script. With no matching font installed, Pillow's built-in font is used. On a minimal
+Linux server, `apt install fonts-liberation` gives good results.
+
+## Speed
+
+In testing, painting at 150 dpi took about **100–200 ms per page**, on top of pdfsieve's reading
+time; text-heavy pages take longest. Turning off `antialias` cut that to **20–130 ms**, at the
+cost of rougher edges. For OCR, antialiasing usually helps accuracy, so keep it on there.
+
+## Development
+
+```bash
+git clone https://github.com/Vibhu1712/pdfpainter
+cd pdfpainter
+pip install -e ".[test]"
+pytest
+```
+
+The tests build their sample PDFs at run time (with reportlab, plus a few hand-written PDFs for
+image formats), and compare page sizes against PDFium when pypdfium2 is installed.
+
+## Licence
+
+Apache License 2.0; see [LICENSE](LICENSE). Copyright 2026 Vaibhav Rawat (AdRaw App Studio).
+Dependencies and their licences are listed in [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md).
+
+pdfpainter began as the fallback page painter inside **docextract by AdRaw App Studio**, an
+offline PDF-to-Excel extraction tool, and is published so others can use it too.