Commit
·
96b0e0e
1
Parent(s):
cb39e46
Updated Windows Tesseract install location for test
Browse files- .github/workflows/multi-os-test.yml +2 -2
- README.md +2 -2
- pyproject.toml +1 -1
.github/workflows/multi-os-test.yml
CHANGED
@@ -57,7 +57,7 @@ jobs:
|
|
57 |
}
|
58 |
|
59 |
# Download and install Tesseract
|
60 |
-
$tesseractUrl = "https://github.com/
|
61 |
$tesseractInstaller = "C:\tools\tesseract-installer.exe"
|
62 |
Invoke-WebRequest -Uri $tesseractUrl -OutFile $tesseractInstaller
|
63 |
|
@@ -65,7 +65,7 @@ jobs:
|
|
65 |
Start-Process -FilePath $tesseractInstaller -ArgumentList "/S", "/D=C:\tools\tesseract" -Wait
|
66 |
|
67 |
# Download and extract Poppler
|
68 |
-
$popplerUrl = "https://github.com/oschwartz10612/poppler-windows/releases/download/
|
69 |
$popplerZip = "C:\tools\poppler.zip"
|
70 |
Invoke-WebRequest -Uri $popplerUrl -OutFile $popplerZip
|
71 |
|
|
|
57 |
}
|
58 |
|
59 |
# Download and install Tesseract
|
60 |
+
$tesseractUrl = "https://github.com/tesseract-ocr/tesseract/releases/download/5.5.0/tesseract-ocr-w64-setup-5.5.0.20241111.exe"
|
61 |
$tesseractInstaller = "C:\tools\tesseract-installer.exe"
|
62 |
Invoke-WebRequest -Uri $tesseractUrl -OutFile $tesseractInstaller
|
63 |
|
|
|
65 |
Start-Process -FilePath $tesseractInstaller -ArgumentList "/S", "/D=C:\tools\tesseract" -Wait
|
66 |
|
67 |
# Download and extract Poppler
|
68 |
+
$popplerUrl = "https://github.com/oschwartz10612/poppler-windows/releases/download/v25.07.0-0/Release-25.07.0-0.zip"
|
69 |
$popplerZip = "C:\tools\poppler.zip"
|
70 |
Invoke-WebRequest -Uri $popplerUrl -OutFile $popplerZip
|
71 |
|
README.md
CHANGED
@@ -10,7 +10,7 @@ license: agpl-3.0
|
|
10 |
---
|
11 |
# Document redaction
|
12 |
|
13 |
-
version: 1.
|
14 |
|
15 |
Redact personally identifiable information (PII) from documents (pdf, images), Word files (.docx), or tabular data (xlsx/csv/parquet). Please see the [User Guide](#user-guide) for a walkthrough on how to use the app. Below is a very brief overview.
|
16 |
|
@@ -44,7 +44,7 @@ Installation on Windows requires downloading installers and adding the programs
|
|
44 |
|
45 |
|
46 |
2. **Install Poppler:**
|
47 |
-
* Download the latest Poppler binary for Windows. A common source is the [Poppler for Windows](https://github.com/oschwartz10612/poppler-windows) GitHub releases page. Download the `.zip` file (e.g., `poppler-
|
48 |
* Extract the contents of the zip file to a permanent location on your computer, for example, `C:\Program Files\poppler\`.
|
49 |
* You must add the `bin` folder from your Poppler installation to your system's PATH environment variable.
|
50 |
* Search for "Edit the system environment variables" in the Windows Start Menu and open it.
|
|
|
10 |
---
|
11 |
# Document redaction
|
12 |
|
13 |
+
version: 1.2.0
|
14 |
|
15 |
Redact personally identifiable information (PII) from documents (pdf, images), Word files (.docx), or tabular data (xlsx/csv/parquet). Please see the [User Guide](#user-guide) for a walkthrough on how to use the app. Below is a very brief overview.
|
16 |
|
|
|
44 |
|
45 |
|
46 |
2. **Install Poppler:**
|
47 |
+
* Download the latest Poppler binary for Windows. A common source is the [Poppler for Windows](https://github.com/oschwartz10612/poppler-windows) GitHub releases page. Download the `.zip` file (e.g., `poppler-25.07.0-win.zip`).
|
48 |
* Extract the contents of the zip file to a permanent location on your computer, for example, `C:\Program Files\poppler\`.
|
49 |
* You must add the `bin` folder from your Poppler installation to your system's PATH environment variable.
|
50 |
* Search for "Edit the system environment variables" in the Windows Start Menu and open it.
|
pyproject.toml
CHANGED
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
4 |
|
5 |
[project]
|
6 |
name = "doc_redaction"
|
7 |
-
version = "1.
|
8 |
description = "Redact PDF/image-based documents, or CSV/XLSX files using a Gradio-based GUI interface"
|
9 |
readme = "README.md"
|
10 |
requires-python = ">=3.10"
|
|
|
4 |
|
5 |
[project]
|
6 |
name = "doc_redaction"
|
7 |
+
version = "1.2.0"
|
8 |
description = "Redact PDF/image-based documents, or CSV/XLSX files using a Gradio-based GUI interface"
|
9 |
readme = "README.md"
|
10 |
requires-python = ">=3.10"
|