topo_map_processor 0.1.6__tar.gz → 0.1.8__tar.gz

{topo_map_processor-0.1.6 → topo_map_processor-0.1.8}/.gitignore

@@ -1,5 +1,6 @@
 # Python-generated files
 __pycache__/
+topo_map_processor/_version.py
 *.py[oc]
 build/
 dist/

{topo_map_processor-0.1.6 → topo_map_processor-0.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: topo_map_processor
-Version: 0.1.6
+Version: 0.1.8
 Summary: Library for processing topographic maps
 Project-URL: homepage, https://github.com/ramSeraph/topo_map_processor
 Project-URL: repository, https://github.com/ramSeraph/topo_map_processor.git
@@ -31,17 +31,20 @@ License: This is free and unencumbered software released into the public domain.
         For more information, please refer to <https://unlicense.org>
 License-File: LICENSE
 Requires-Python: >=3.12
-Requires-Dist: easyocr>=1.7.2
-Requires-Dist: imgcat>=0.6.0
 Requires-Dist: mercantile>=1.2.1
-Requires-Dist: numpy>=2.3.1
-Requires-Dist: opencv-python-headless>=4.11.0.86
-Requires-Dist: pillow>=11.3.0
 Requires-Dist: pmtiles>=3.4.1
-Requires-Dist: pyproj>=3.7.1
-Requires-Dist: pytesseract>=0.3.13
-Requires-Dist: rasterio>=1.4.3
+Requires-Dist: requests>=2.32.4
 Requires-Dist: shapely>=2.1.1
+Provides-Extra: easyocr
+Requires-Dist: easyocr>=1.7.2; extra == 'easyocr'
+Provides-Extra: parse
+Requires-Dist: imgcat>=0.6.0; extra == 'parse'
+Requires-Dist: numpy>=2.3.1; extra == 'parse'
+Requires-Dist: opencv-python-headless>=4.11.0.86; extra == 'parse'
+Requires-Dist: pillow>=11.3.0; extra == 'parse'
+Requires-Dist: pyproj>=3.7.1; extra == 'parse'
+Requires-Dist: pytesseract>=0.3.13; extra == 'parse'
+Requires-Dist: rasterio>=1.4.3; extra == 'parse'
 Description-Content-Type: text/markdown
 
 # Topo Map Processor [![PyPI - Latest Version](https://img.shields.io/pypi/v/topo_map_processor)](https://pypi.org/project/topo_map_processor/) [![GitHub Tag](https://img.shields.io/github/v/tag/ramSeraph/topo_map_processor?filter=v*)](https://github.com/ramSeraph/topo_map_processor/releases/latest)
@@ -119,7 +122,7 @@ The `TopoMapProcessor` class provides a framework for processing individual map
 Here's an example of how to use the `TopoMapProcessor` class.
 
 ```python
-from topo_map_processor import TopoMapProcessor, LineRemovalParams
+from topo_map_processor.processor import TopoMapProcessor, LineRemovalParams
 
 class SampleProcessor(TopoMapProcessor):
 
@@ -205,6 +208,15 @@ Similar to corner detection, the `locate_grid_lines` method can be implemented u
 
 -   **`get_grid_line_corrections`**: This method serves as a refinement step to improve accuracy. While the transformer provides a very close estimate, this function can correct for minor printing or scanning inaccuracies. For each projected grid intersection, it searches a small area in the actual image for the *true* intersection of printed lines, adjusting the point to match the visual data. This ensures that the lines targeted for removal are precisely the ones printed on the map.
 
+### Tile Sources
+
+The `topo_map_processor.tools.tile_sources` module provides classes for reading tiles from different sources.
+
+-   `DiskTilesSource`: Reads tiles from a directory on the local disk.
+-   `MBTilesSource`: Reads tiles from an MBTiles file.
+-   `PMTilesSource`: Reads tiles from a PMTiles file.
+-   `StackedTileSource`: Combines multiple tile sources (Disk, MBTiles, PMTiles) into a single logical source, allowing for seamless access across different storage types.
+
 ### Command-Line Tools
 
 This project provides several command-line tools to work with topographic maps. These tools are dynamically loaded, and you can get the most up-to-date usage information by running the tool with the `--help` flag.
@@ -221,24 +233,37 @@ collect-bounds --bounds-dir <directory> --output-file <file> [--preexisting-file
 -   `--output-file`: Output GeoJSON file path. (Required)
 -   `--preexisting-file`: Pre existing GeoJSON file path. (Optional)
 
+#### `download-mosaic`
+
+Downloads a PMTiles mosaic and converts it to a single MBTiles file. A mosaic is a JSON file that lists multiple PMTiles files.
+
+```bash
+download-mosaic --mosaic_url <url> [--output_file <file>] [--request-timeout-secs <seconds>] [--num-http-retries <retries>]
+```
+
+-   `--mosaic_url`, `-u`: URL of the mosaic JSON file. (Required)
+-   `--output_file`, `-o`: Output MBTiles file name. If not specified, it is derived from the mosaic URL. (Optional)
+-   `--request-timeout-secs`, `-t`: Timeout for HTTP requests in seconds (default: 60).
+-   `--num-http-retries`, `-r`: Number of retries for HTTP requests (default: 3).
+
 #### `partition`
 
-Partitions a large set of tiles into smaller PMTiles files. This is useful for managing large datasets, for example, to stay within file size limits for services like GitHub Releases. When run with `--only-disk`, it creates a new partitioned `pmtiles` fileset from a directory of tiles. When run without, it can be used to re-partition an existing `pmtiles` fileset, for example after having retiled some of the sheets.
+Partitions a large set of tiles into smaller PMTiles files. This is useful for managing large datasets, for example, to stay within file size limits for services like GitHub Releases. It creates a mosaic file if the output is partitioned into multiple files.
 
 ```bash
-partition --to-pmtiles-prefix <prefix> --from-tiles-dir <dir> [--from-pmtiles-prefix <prefix>] [--name <name>] [--description <desc>] [--max-zoom <zoom>] [--min-zoom <zoom>] [--only-disk] (--attribution <text> | --attribution-file <file>)
+partition --from-source <source> [--from-source <source> ...] --to-pmtiles <file> [--size-limit <limit>]
 ```
 
--   `--to-pmtiles-prefix`: Prefix for the output PMTiles files. (Required)
--   `--from-tiles-dir`: Directory containing the input tiles. (Required)
--   `--from-pmtiles-prefix`: Prefix for input PMTiles files (required if not using `--only-disk`).
--   `--name`: Name of the mosaic. (Required if using `--only-disk`)
--   `--description`: Description of the mosaic. (Required if using `--only-disk`)
--   `--max-zoom`: Maximum zoom level for the mosaic. (Defaults to the max zoom found in the source)
--   `--min-zoom`: Minimum zoom level for the mosaic (default: 0).
--   `--only-disk`: Only read tiles from the local disk.
--   `--attribution`: Attribution text for the mosaic. (Required if using `--only-disk`)
--   `--attribution-file`: File containing attribution text. (Required if using `--only-disk`)
+-   `--from-source`: Path to a source file or directory. Can be repeated. Supported sources:
+    -   `.mbtiles` file: e.g., `path/to/file.mbtiles`
+    -   `.pmtiles` file (supports glob patterns): e.g., `path/to/*.pmtiles`
+    -   Directory containing tiles: e.g., `path/to/tiles_dir`
+-   `--to-pmtiles`: Output PMTiles file. The prefix for partitioned files will be derived from this argument.
+-   `--size-limit`: Maximum size of each partition. Can be a number in bytes (e.g., `100000000`), or with units (e.g., `100M`, `2G`), or a preset:
+    -   `github_release`: 2GB limit
+    -   `github_file`: 100MB limit
+    -   `cloudflare_object`: 512MB limit
+    The overhead (delta) is scaled proportionally based on the `github_release` preset (2GB with 5MB overhead). Defaults to `github_release`.
 
 #### `retile`
 
@@ -249,30 +274,38 @@ The tool works in two stages. First, it calculates the full set of sheets that n
 In the second stage, it retiles the affected area. It uses the pull list to create a temporary virtual raster (`.vrt`), generates new base tiles for the affected region, and then reconstructs the upper-level tiles by pulling existing, unaffected tiles from the PMTiles source.
 
 ```bash
-retile --retile-list-file <file> --bounds-file <file> [--max-zoom <zoom>] [--min-zoom <zoom>] [--tiffs-dir <dir>] [--tiles-dir <dir>] [--from-pmtiles-prefix <prefix>] [--sheets-to-pull-list-outfile <file>]
+retile --retile-list-file <file> --bounds-file <file> [--max-zoom <zoom>] [--tiffs-dir <dir>] [--tiles-dir <dir>] [--from-source <source>] [--sheets-to-pull-list-outfile <file>] [--num-parallel <processes>] [--tile-quality <quality>]
 ```
 
 -   `--retile-list-file`: File containing the list of sheets to retile. (Required)
 -   `--bounds-file`: GeoJSON file containing the list of available sheets and their geographic bounds. (Required)
--   `--max-zoom`: Maximum zoom level to create tiles for. (Defaults to the max zoom from the PMTiles source)
--   `--min-zoom`: Minimum zoom level to create tiles for. (Defaults to the min zoom from the PMTiles source)
+-   `--max-zoom`: Maximum zoom level to create tiles for. Defaults to the max zoom from the source if `--from-source` is provided, otherwise it is required.
 -   `--tiffs-dir`: Directory where the GeoTIFFs are located. (Required if not in pull-list generation mode)
 -   `--tiles-dir`: Directory where the tiles will be created. (Required if not in pull-list generation mode)
--   `--from-pmtiles-prefix`: Prefix for the PMTiles source from which to pull existing tiles. (Required if not in pull-list generation mode)
+-   `--from-source`: Location of the source from which to pull existing tiles. Can be a glob pattern to match a group of pmtiles. Required if not in pull-list generation mode.
 -   `--sheets-to-pull-list-outfile`: If provided, the script will only calculate the full list of sheets that need to be processed (including adjacent ones) and write it to this file, then exit.
+-   `--num-parallel`: Number of parallel processes to use for tiling (default: number of CPU cores).
+-   `--tile-quality`: Quality of compression for webp and jpg (default: 75).
 
 #### `tile`
 
 Creates web map tiles from a directory of GeoTIFF files. It combines them into a virtual raster (`.vrt`) for efficient processing.
 
 ```bash
-tile <tiles-dir> <tiffs-dir> <max-zoom> [<min-zoom>]
+tile --tiles-dir <dir> --tiffs-dir <dir> --max-zoom <zoom> --name <name> --description <desc> (--attribution <text> | --attribution-file <file>) [--min-zoom <zoom>] [--tile-extension <ext>] [--tile-quality <quality>] [--num-parallel <processes>]
 ```
 
--   `<tiles-dir>`: Directory to store the output tiles. (Required)
--   `<tiffs-dir>`: Directory containing the input GeoTIFF files. (Required)
--   `<max-zoom>`: Maximum zoom level for tiling. (Required)
--   `<min-zoom>`: Minimum zoom level for tiling (default: 0).
+-   `--tiles-dir`: Directory to store the output tiles. (Required)
+-   `--tiffs-dir`: Directory containing the input GeoTIFF files. (Required)
+-   `--max-zoom`: Maximum zoom level for tiling. (Required)
+-   `--name`: Name of the mosaic. (Required)
+-   `--description`: Description of the mosaic. (Required)
+-   `--attribution`: Attribution text for the mosaic. Required if `--attribution-file` is not used.
+-   `--attribution-file`: File containing attribution text for the mosaic. Required if `--attribution` is not used.
+-   `--min-zoom`: Minimum zoom level for tiling (default: 0).
+-   `--tile-extension`: Tile file extension (default: webp). Choices: `webp`, `jpg`, `jpeg`, `png`.
+-   `--tile-quality`: Compression quality of the tiles for `webp` and `jpg` (default: 75).
+-   `--num-parallel`: Number of parallel processes to use for tiling (default: number of CPU cores).
 
 ### Running Tools Directly with `uvx`
 

{topo_map_processor-0.1.6 → topo_map_processor-0.1.8}/README.md

@@ -73,7 +73,7 @@ The `TopoMapProcessor` class provides a framework for processing individual map
 Here's an example of how to use the `TopoMapProcessor` class.
 
 ```python
-from topo_map_processor import TopoMapProcessor, LineRemovalParams
+from topo_map_processor.processor import TopoMapProcessor, LineRemovalParams
 
 class SampleProcessor(TopoMapProcessor):
 
@@ -159,6 +159,15 @@ Similar to corner detection, the `locate_grid_lines` method can be implemented u
 
 -   **`get_grid_line_corrections`**: This method serves as a refinement step to improve accuracy. While the transformer provides a very close estimate, this function can correct for minor printing or scanning inaccuracies. For each projected grid intersection, it searches a small area in the actual image for the *true* intersection of printed lines, adjusting the point to match the visual data. This ensures that the lines targeted for removal are precisely the ones printed on the map.
 
+### Tile Sources
+
+The `topo_map_processor.tools.tile_sources` module provides classes for reading tiles from different sources.
+
+-   `DiskTilesSource`: Reads tiles from a directory on the local disk.
+-   `MBTilesSource`: Reads tiles from an MBTiles file.
+-   `PMTilesSource`: Reads tiles from a PMTiles file.
+-   `StackedTileSource`: Combines multiple tile sources (Disk, MBTiles, PMTiles) into a single logical source, allowing for seamless access across different storage types.
+
 ### Command-Line Tools
 
 This project provides several command-line tools to work with topographic maps. These tools are dynamically loaded, and you can get the most up-to-date usage information by running the tool with the `--help` flag.
@@ -175,24 +184,37 @@ collect-bounds --bounds-dir <directory> --output-file <file> [--preexisting-file
 -   `--output-file`: Output GeoJSON file path. (Required)
 -   `--preexisting-file`: Pre existing GeoJSON file path. (Optional)
 
+#### `download-mosaic`
+
+Downloads a PMTiles mosaic and converts it to a single MBTiles file. A mosaic is a JSON file that lists multiple PMTiles files.
+
+```bash
+download-mosaic --mosaic_url <url> [--output_file <file>] [--request-timeout-secs <seconds>] [--num-http-retries <retries>]
+```
+
+-   `--mosaic_url`, `-u`: URL of the mosaic JSON file. (Required)
+-   `--output_file`, `-o`: Output MBTiles file name. If not specified, it is derived from the mosaic URL. (Optional)
+-   `--request-timeout-secs`, `-t`: Timeout for HTTP requests in seconds (default: 60).
+-   `--num-http-retries`, `-r`: Number of retries for HTTP requests (default: 3).
+
 #### `partition`
 
-Partitions a large set of tiles into smaller PMTiles files. This is useful for managing large datasets, for example, to stay within file size limits for services like GitHub Releases. When run with `--only-disk`, it creates a new partitioned `pmtiles` fileset from a directory of tiles. When run without, it can be used to re-partition an existing `pmtiles` fileset, for example after having retiled some of the sheets.
+Partitions a large set of tiles into smaller PMTiles files. This is useful for managing large datasets, for example, to stay within file size limits for services like GitHub Releases. It creates a mosaic file if the output is partitioned into multiple files.
 
 ```bash
-partition --to-pmtiles-prefix <prefix> --from-tiles-dir <dir> [--from-pmtiles-prefix <prefix>] [--name <name>] [--description <desc>] [--max-zoom <zoom>] [--min-zoom <zoom>] [--only-disk] (--attribution <text> | --attribution-file <file>)
+partition --from-source <source> [--from-source <source> ...] --to-pmtiles <file> [--size-limit <limit>]
 ```
 
--   `--to-pmtiles-prefix`: Prefix for the output PMTiles files. (Required)
--   `--from-tiles-dir`: Directory containing the input tiles. (Required)
--   `--from-pmtiles-prefix`: Prefix for input PMTiles files (required if not using `--only-disk`).
--   `--name`: Name of the mosaic. (Required if using `--only-disk`)
--   `--description`: Description of the mosaic. (Required if using `--only-disk`)
--   `--max-zoom`: Maximum zoom level for the mosaic. (Defaults to the max zoom found in the source)
--   `--min-zoom`: Minimum zoom level for the mosaic (default: 0).
--   `--only-disk`: Only read tiles from the local disk.
--   `--attribution`: Attribution text for the mosaic. (Required if using `--only-disk`)
--   `--attribution-file`: File containing attribution text. (Required if using `--only-disk`)
+-   `--from-source`: Path to a source file or directory. Can be repeated. Supported sources:
+    -   `.mbtiles` file: e.g., `path/to/file.mbtiles`
+    -   `.pmtiles` file (supports glob patterns): e.g., `path/to/*.pmtiles`
+    -   Directory containing tiles: e.g., `path/to/tiles_dir`
+-   `--to-pmtiles`: Output PMTiles file. The prefix for partitioned files will be derived from this argument.
+-   `--size-limit`: Maximum size of each partition. Can be a number in bytes (e.g., `100000000`), or with units (e.g., `100M`, `2G`), or a preset:
+    -   `github_release`: 2GB limit
+    -   `github_file`: 100MB limit
+    -   `cloudflare_object`: 512MB limit
+    The overhead (delta) is scaled proportionally based on the `github_release` preset (2GB with 5MB overhead). Defaults to `github_release`.
 
 #### `retile`
 
@@ -203,30 +225,38 @@ The tool works in two stages. First, it calculates the full set of sheets that n
 In the second stage, it retiles the affected area. It uses the pull list to create a temporary virtual raster (`.vrt`), generates new base tiles for the affected region, and then reconstructs the upper-level tiles by pulling existing, unaffected tiles from the PMTiles source.
 
 ```bash
-retile --retile-list-file <file> --bounds-file <file> [--max-zoom <zoom>] [--min-zoom <zoom>] [--tiffs-dir <dir>] [--tiles-dir <dir>] [--from-pmtiles-prefix <prefix>] [--sheets-to-pull-list-outfile <file>]
+retile --retile-list-file <file> --bounds-file <file> [--max-zoom <zoom>] [--tiffs-dir <dir>] [--tiles-dir <dir>] [--from-source <source>] [--sheets-to-pull-list-outfile <file>] [--num-parallel <processes>] [--tile-quality <quality>]
 ```
 
 -   `--retile-list-file`: File containing the list of sheets to retile. (Required)
 -   `--bounds-file`: GeoJSON file containing the list of available sheets and their geographic bounds. (Required)
--   `--max-zoom`: Maximum zoom level to create tiles for. (Defaults to the max zoom from the PMTiles source)
--   `--min-zoom`: Minimum zoom level to create tiles for. (Defaults to the min zoom from the PMTiles source)
+-   `--max-zoom`: Maximum zoom level to create tiles for. Defaults to the max zoom from the source if `--from-source` is provided, otherwise it is required.
 -   `--tiffs-dir`: Directory where the GeoTIFFs are located. (Required if not in pull-list generation mode)
 -   `--tiles-dir`: Directory where the tiles will be created. (Required if not in pull-list generation mode)
--   `--from-pmtiles-prefix`: Prefix for the PMTiles source from which to pull existing tiles. (Required if not in pull-list generation mode)
+-   `--from-source`: Location of the source from which to pull existing tiles. Can be a glob pattern to match a group of pmtiles. Required if not in pull-list generation mode.
 -   `--sheets-to-pull-list-outfile`: If provided, the script will only calculate the full list of sheets that need to be processed (including adjacent ones) and write it to this file, then exit.
+-   `--num-parallel`: Number of parallel processes to use for tiling (default: number of CPU cores).
+-   `--tile-quality`: Quality of compression for webp and jpg (default: 75).
 
 #### `tile`
 
 Creates web map tiles from a directory of GeoTIFF files. It combines them into a virtual raster (`.vrt`) for efficient processing.
 
 ```bash
-tile <tiles-dir> <tiffs-dir> <max-zoom> [<min-zoom>]
+tile --tiles-dir <dir> --tiffs-dir <dir> --max-zoom <zoom> --name <name> --description <desc> (--attribution <text> | --attribution-file <file>) [--min-zoom <zoom>] [--tile-extension <ext>] [--tile-quality <quality>] [--num-parallel <processes>]
 ```
 
--   `<tiles-dir>`: Directory to store the output tiles. (Required)
--   `<tiffs-dir>`: Directory containing the input GeoTIFF files. (Required)
--   `<max-zoom>`: Maximum zoom level for tiling. (Required)
--   `<min-zoom>`: Minimum zoom level for tiling (default: 0).
+-   `--tiles-dir`: Directory to store the output tiles. (Required)
+-   `--tiffs-dir`: Directory containing the input GeoTIFF files. (Required)
+-   `--max-zoom`: Maximum zoom level for tiling. (Required)
+-   `--name`: Name of the mosaic. (Required)
+-   `--description`: Description of the mosaic. (Required)
+-   `--attribution`: Attribution text for the mosaic. Required if `--attribution-file` is not used.
+-   `--attribution-file`: File containing attribution text for the mosaic. Required if `--attribution` is not used.
+-   `--min-zoom`: Minimum zoom level for tiling (default: 0).
+-   `--tile-extension`: Tile file extension (default: webp). Choices: `webp`, `jpg`, `jpeg`, `png`.
+-   `--tile-quality`: Compression quality of the tiles for `webp` and `jpg` (default: 75).
+-   `--num-parallel`: Number of parallel processes to use for tiling (default: number of CPU cores).
 
 ### Running Tools Directly with `uvx`
 

{topo_map_processor-0.1.6 → topo_map_processor-0.1.8}/pyproject.toml

@@ -8,22 +8,29 @@ authors = [
     { name = "Sreeram Kandimalla", email = "kandimalla.sreeram@gmail.com" },
 ]
 dependencies = [
-    "easyocr>=1.7.2",
-    "imgcat>=0.6.0",
     "mercantile>=1.2.1",
-    "numpy>=2.3.1",
-    "opencv-python-headless>=4.11.0.86",
-    "pillow>=11.3.0",
     "pmtiles>=3.4.1",
-    "pyproj>=3.7.1",
-    "pytesseract>=0.3.13",
-    "rasterio>=1.4.3",
+    "requests>=2.32.4",
     "shapely>=2.1.1",
 ]
 dynamic = [
     "version"
 ]
 
+[project.optional-dependencies]
+easyocr = [
+    "easyocr>=1.7.2",
+]
+parse = [
+    "numpy>=2.3.1",
+    "pillow>=11.3.0",
+    "imgcat>=0.6.0",
+    "opencv-python-headless>=4.11.0.86",
+    "pyproj>=3.7.1",
+    "pytesseract>=0.3.13",
+    "rasterio>=1.4.3",
+]
+
 [project.urls]
 homepage = "https://github.com/ramSeraph/topo_map_processor"
 repository = "https://github.com/ramSeraph/topo_map_processor.git"
@@ -31,9 +38,12 @@ repository = "https://github.com/ramSeraph/topo_map_processor.git"
 
 [project.scripts]
 collect-bounds = "topo_map_processor.tools.collect_bounds:cli"
+download-mosaic = "topo_map_processor.tools.download_mosaic:cli"
 partition = "topo_map_processor.tools.partition:cli"
 retile = "topo_map_processor.tools.retile:cli"
 tile = "topo_map_processor.tools.tile:cli"
+generate-lists = "topo_map_processor.tools.execute_bash:generate_lists"
+upload-to-release = "topo_map_processor.tools.execute_bash:upload_to_release"
 
 
 [build-system]
@@ -49,6 +59,15 @@ source = "vcs"
 [tool.hatch.build.hooks.vcs]
 version-file = "topo_map_processor/_version.py"
 
-tool.hatch.build.targets.sdist.include = [
-    "topo_map_processor"
+[tool.hatch.build.targets.sdist]
+include = [
+    "topo_map_processor",
+    "topo_map_processor/bash_scripts/**",
 ]
+
+[tool.hatch.build.targets.wheel]
+include = [
+    "topo_map_processor",
+    "topo_map_processor/bash_scripts/**",
+]
+

{topo_map_processor-0.1.6 → topo_map_processor-0.1.8}/topo_map_processor/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.6'
-__version_tuple__ = version_tuple = (0, 1, 6)
+__version__ = version = '0.1.8'
+__version_tuple__ = version_tuple = (0, 1, 8)

topo_map_processor-0.1.8/topo_map_processor/bash_scripts/generate_lists.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+
+prog_name=${COMMNAND_NAME:-$(basename "$0")}
+release_base=$1
+ext=$2
+
+if [ -z "$release_base" ] || [ -z "$ext" ]; then
+  echo "Usage: $prog_name <release_base> <extension>"
+  exit 1
+fi
+
+#owner=$(gh repo view --json owner -q .owner.login)
+#name=$(gh repo view --json name -q .name)
+#repo="$owner/$name"
+
+echo "getting file list"
+echo "name,size,url" > listing_files.csv
+
+# Get all releases, then filter for the base release and any -extra releases.
+releases_to_process=$(gh release list --repo "$repo" --json tagName -q '.[].tagName' | grep -E "^${release_base}(-extra[0-9]+)?$")
+releases_to_process=$(echo "$releases_to_process" | sort -u)
+
+echo "Will process releases: $releases_to_process"
+
+for release in $releases_to_process; do
+  echo "Processing release: $release"
+  gh release view "$release" --json assets -q ".assets[] | select(.name | endswith(\"$ext\")) | \"\\(.name),\\(.size),\\(.url)\"" >> listing_files.csv
+done
+
+gh release upload "$release_base" listing_files.csv --clobber
+
+rm listing_files.csv
+

topo_map_processor-0.1.8/topo_map_processor/bash_scripts/upload_to_release.sh

@@ -0,0 +1,149 @@
+#!/bin/bash
+
+# A script to upload files from a folder to a GitHub release,
+# skipping files that already exist in the release.
+# If the fourth argument is 'yes', it will overwrite existing assets.
+
+set -e
+set -o pipefail
+
+# --- Configuration ---
+# TAG: The git tag of the release to upload to.
+# FOLDER: The local folder containing the files to upload.
+# OVERWRITE: Optional. Set to 'yes' to allow overwriting existing assets.
+prog_name=${COMMNAND_NAME:-$(basename "$0")}
+
+if [ "$#" -lt 3 ] || [ "$#" -gt 4 ]; then
+    echo "Usage: $prog_name <tag> <folder> <extension_without_the_leading_dot> [yes_to_overwrite]"
+    exit 1
+fi
+
+TAG="$1"
+FOLDER="$2"
+EXT="$3"
+OVERWRITE_FLAG=${4:-no}
+
+# --- Pre-flight Checks ---
+
+# Check if gh is installed
+if ! command -v gh &> /dev/null; then
+    echo "Error: gh command-line tool is not installed. Please install it to continue."
+    exit 1
+fi
+
+if [ -z "$TAG" ]; then
+    echo "Error: Release tag is not specified."
+    exit 1
+fi
+
+if [ ! -d "$FOLDER" ]; then
+    echo "Error: Folder '$FOLDER' not found."
+    exit 1
+fi
+
+if [ -z "$EXT" ]; then
+    echo "Error: Extension '$EXT' is not specified."
+    exit 1
+fi
+
+ALLOW_OVERWRITE=0
+if [ "$OVERWRITE_FLAG" == "yes" ]; then
+    ALLOW_OVERWRITE=1
+    echo "Overwrite flag is set. Existing assets will be overwritten."
+fi
+
+# --- Main Logic ---
+
+echo "Fetching existing assets for releases matching pattern '${TAG}(-extra[0-9]+)?'..."
+
+# Get all releases, then filter for the base release and any -extra releases, and sort them
+RELEASES_TO_PROCESS=$(gh release list --json tagName -q '.[].tagName' | grep -E "^${TAG}(-extra[0-9]+)?$" | sort -V)
+
+if [ -z "$RELEASES_TO_PROCESS" ]; then
+    echo "Error: No releases found matching pattern '${TAG}(-extra[0-9]+)?'." >&2
+    exit 1
+fi
+
+echo "Found releases: $RELEASES_TO_PROCESS"
+
+# Store assets with their release tags. Format: "asset_name release_tag"
+EXISTING_ASSETS_WITH_RELEASES=""
+for release in $RELEASES_TO_PROCESS; do
+  echo "Fetching assets from release: $release"
+  assets=$(gh release view "$release" --json assets -q '.assets[].name' 2>/dev/null || echo "")
+  if [ -n "$assets" ]; then
+    while IFS= read -r asset_name; do
+      if [ -n "$asset_name" ]; then
+        EXISTING_ASSETS_WITH_RELEASES="${EXISTING_ASSETS_WITH_RELEASES}${asset_name} ${release}"$'
+'
+      fi
+    done <<< "$assets"
+  fi
+done
+
+if [ -z "$EXISTING_ASSETS_WITH_RELEASES" ]; then
+    echo "Could not fetch any assets. This could mean the releases do not have assets, or you lack permissions."
+fi
+
+# Determine available releases and their current asset counts
+AVAILABLE_RELEASES=()
+AVAILABLE_ASSET_COUNTS=()
+for release in $RELEASES_TO_PROCESS; do
+    count=$(gh release view "$release" --json assets -q '.assets | length' 2>/dev/null || echo "0")
+    
+    MAX_ASSETS=998
+    if [ "$release" == "$TAG" ]; then
+        MAX_ASSETS=988
+    fi
+
+    if [ "$count" -lt "$MAX_ASSETS" ]; then
+        AVAILABLE_RELEASES+=("$release")
+        AVAILABLE_ASSET_COUNTS+=("$count")
+    fi
+done
+
+echo "Starting upload process from folder '$FOLDER'..."
+
+# Find all files in the folder that are not yet in any release and loop through them.
+find "${FOLDER}" -type f | grep "^.*\.${EXT}$" | while read -r FILE_PATH; do
+    FILENAME=$(basename "$FILE_PATH")
+
+    RELEASE_FOR_ASSET=$(echo -n "$EXISTING_ASSETS_WITH_RELEASES" | grep "^${FILENAME} " | head -n 1 | awk '{print $2}')
+
+    if [ -n "$RELEASE_FOR_ASSET" ]; then
+        # Asset exists
+        if [ "$ALLOW_OVERWRITE" -eq 1 ]; then
+            echo "  -> Overwriting '$FILENAME' in release '$RELEASE_FOR_ASSET'..."
+            gh release upload "$RELEASE_FOR_ASSET" "$FILE_PATH" --clobber
+        else
+            echo "  -> Skipping '$FILENAME', it already exists in release '$RELEASE_FOR_ASSET'."
+        fi
+        continue
+    fi
+
+    # Find a release to upload to for a new asset
+    if [ ${#AVAILABLE_RELEASES[@]} -eq 0 ]; then
+        echo "Error: All existing releases are full. No space to upload '$FILENAME'." >&2
+        exit 1
+    fi
+
+    UPLOAD_TARGET=${AVAILABLE_RELEASES[0]}
+
+    echo "  -> Uploading '$FILENAME' to '$UPLOAD_TARGET'..."
+    gh release upload "$UPLOAD_TARGET" "$FILE_PATH"
+
+    # Update asset count and remove release from available list if full
+    AVAILABLE_ASSET_COUNTS[0]=$((${AVAILABLE_ASSET_COUNTS[0]} + 1))
+    
+    MAX_ASSETS=998
+    if [ "$UPLOAD_TARGET" == "$TAG" ]; then
+        MAX_ASSETS=988
+    fi
+
+    if [ "${AVAILABLE_ASSET_COUNTS[0]}" -ge "$MAX_ASSETS" ]; then
+        AVAILABLE_RELEASES=("${AVAILABLE_RELEASES[@]:1}")
+        AVAILABLE_ASSET_COUNTS=("${AVAILABLE_ASSET_COUNTS[@]:1}")
+    fi
+done
+
+echo "Upload process complete."

topo_map_processor-0.1.6/topo_map_processor/__init__.py → topo_map_processor-0.1.8/topo_map_processor/processor.py

@@ -14,7 +14,6 @@ import cv2
 import numpy as np
 
 import pytesseract
-import easyocr
 from PIL import Image
 from imgcat import imgcat
 
@@ -551,6 +550,7 @@ class TopoMapProcessor:
         global easy_ocr_reader
     
         if easy_ocr_reader is None:
+            import easyocr
             easy_ocr_reader = easyocr.Reader(['en'], gpu=False)
     
         mask = np.zeros(img.shape[:2], dtype=np.uint8)