Support direct path to a raster file in file_path parameter

CHANGELOG.md

@@ -11,7 +11,7 @@
 ### Changes
 - [#1168](https://github.com/LayerManager/layman/issues/1168) Extend [PATCH Workspace Layer](doc/rest.md#patch-workspace-layer) with ability of appending data to existing time-series layer.
 - When publishing a layer or map to Micka via CSW, Layman sends the creating user (Layman username) in the SOAP request header (`CreateUser`), so the metadata record in Micka is associated with the user who created the publication.
-- [#1185](https://github.com/LayerManager/layman/issues/1185) POST Workspace [Layers](doc/rest.md#post-workspace-layers) supports import of raster layers from an existing server-side directory via the file_path parameter, including ImageMosaic timeseries layers. 
+- [#1185](https://github.com/LayerManager/layman/issues/1185) POST Workspace [Layers](doc/rest.md#post-workspace-layers) supports import of raster layers from existing server-side data via `file_path` (directory for ImageMosaic timeseries layers, or direct GeoTIFF file path).
 - [#1185](https://github.com/LayerManager/layman/issues/1185)[GET Workspace Layer](doc/rest.md#get-workspace-layer) returns `file_path` key for raster layers published using this parameter.
 
 ## v2.3.0

doc/rest.md

@@ -167,13 +167,16 @@ Body parameters:
   - exactly one of `file`, `file_path`, or `external_table_uri` must be set  
   - relative path to a directory that already exists on the server  
   - the path must be relative to the root of the GeoServer data directory  
-  - the referenced directory must be physically located inside the GeoServer data directory  
-  - the directory must contain at least one GeoTIFF file (with extension `.tif` or `.tiff`)
+  - the referenced path must be physically located inside the GeoServer data directory  
+  - if directory is used, it must contain at least one GeoTIFF file (with extension `.tif` or `.tiff`)
+  - if directory contains more than one raster file, `time_regex` parameter is required
+  - if file is used, it must be a GeoTIFF file (with extension `.tif` or `.tiff`)
 
   - for raster layers:
     - supported only for GeoTIFF files (`.tif` or `.tiff` extension)
     - raster files are not normalized when using `file_path` parameter      
       - this may result in different styling behavior compared to layers published via `file` parameter      
+    - may point directly to a single raster file (published as a single coverage)
     - may point to a directory containing a single raster file (published as a single coverage)
     - may point to a directory containing multiple raster files:
       - if `time_regex` parameter is provided, files are treated as a time series and published as an ImageMosaic
@@ -346,7 +349,7 @@ JSON object with following structure:
   - *status*: Status information about publishing style. See [GET Workspace Layer](#get-workspace-layer) **wms** property for meaning.
   - *error*: If status is FAILURE, this may contain error object.
 - **original_data_source**: String. Either `file` if layer was published from file, or `database_table` if layer was published from external database table 
-- **file_path**: String. Available only for raster layers published using `file_path` parameter. Relative path to the directory containing raster files, relative to the root of the GeoServer data directory.
+- **file_path**: String. Available only for raster layers published using `file_path` parameter. Relative path (to directory or direct GeoTIFF file) inside the root of the GeoServer data directory.
 - *metadata*
   - *identifier*: String. Identifier of metadata record in CSW instance.
   - *record_url*: String. URL of metadata record accessible by web browser, probably with some editing capabilities.

src/layman/layer/filesystem/input_file.py

@@ -86,15 +86,7 @@ def get_file_path_info(publ_uuid):
 
     abs_path = os.path.join(settings.GEOSERVER_DATADIR, file_path_relative)
 
-    if not os.path.isdir(abs_path):
-        raise LaymanError(2, {
-            'parameter': 'file_path',
-            'message': 'Path is not a directory',
-            'expected': 'Relative path to directory containing raster files',
-            'found': file_path_relative,
-        })
-
-    tifs = layer_util.get_geotiff_files(abs_path)
+    tifs = layer_util.get_file_path_geotiff_files(abs_path)
     if not tifs:
         return None
     return [{'absolute': tif, 'gdal': tif, 'file_path': file_path_relative} for tif in tifs]

src/layman/layer/rest_workspace_layers.py

@@ -108,10 +108,15 @@ def post(workspace):
     time_regex = request.form.get('time_regex') or None
     time_regex_format = request.form.get('time_regex_format') or None
 
-    file_path_relative, file_path_absolute, _, _ = util.validate_and_process_file_path(file_path, check_crs=check_crs)
+    file_path_relative, file_path_absolute, file_path_type, tif_files = util.validate_and_process_file_path(file_path, check_crs=check_crs)
     if file_path_relative:
         file_path = file_path_absolute
-        util.validate_file_path_requires_time_regex(file_path_absolute, time_regex)
+        util.validate_file_path_requires_time_regex(
+            file_path_absolute,
+            time_regex,
+            file_path_type=file_path_type,
+            tif_files=tif_files,
+        )
 
     util.validate_time_regex(time_regex, time_regex_format)
     slugified_time_regex = input_file.slugify_timeseries_filename_pattern(time_regex) if time_regex else None
@@ -147,7 +152,6 @@ def post(workspace):
         if file_path:
             geodata_type = settings.GEODATA_TYPE_RASTER
             if not crs_id:
-                tif_files = util.get_geotiff_files(file_path)
                 crs_id = input_file.get_raster_crs_id(tif_files[0]) if tif_files else None
                 if not crs_id:
                     raise LaymanError(4, {'found': None, 'supported_values': settings.INPUT_SRS_LIST})

src/layman/layer/util.py

@@ -1,7 +1,6 @@
 from functools import wraps, partial
 from urllib import parse
 import os
-import glob
 import re
 import logging
 import shutil
@@ -28,6 +27,9 @@
 
 EXTERNAL_TABLE_URI_PATTERN = 'postgresql://<username>:<password>@<host>:<port>/<dbname>?schema=<schema_name>&table=<table_name>&geo_column=<geo_column_name>'
 logger = logging.getLogger(__name__)
+FILE_PATH_TYPE_DIRECTORY = 'directory'
+FILE_PATH_TYPE_FILE = 'file'
+FILE_PATH_MAIN_EXTENSIONS = {ext.lower() for ext in settings.FILE_PATH_MAIN_FILE_EXTENSIONS}
 
 
 def to_safe_layer_name(value):
@@ -254,11 +256,78 @@ def layer_info_to_metadata_properties(info):
 
 
 def get_geotiff_files(directory):
-    files = []
-    for ext in settings.FILE_PATH_MAIN_FILE_EXTENSIONS:
-        files.extend(glob.glob(os.path.join(directory, f'*{ext}')))
-        files.extend(glob.glob(os.path.join(directory, f'*{ext.upper()}')))
-    return files
+    return [
+        os.path.join(directory, f)
+        for f in os.listdir(directory)
+        if os.path.splitext(f)[1].lower() in FILE_PATH_MAIN_EXTENSIONS
+    ]
+
+
+def get_file_path_type(file_path_absolute):
+    if os.path.isdir(file_path_absolute):
+        return FILE_PATH_TYPE_DIRECTORY
+    if os.path.isfile(file_path_absolute):
+        return FILE_PATH_TYPE_FILE
+    return None
+
+
+def get_file_path_geotiff_files(file_path_absolute, *, file_path_type=None):
+    file_path_type = file_path_type or get_file_path_type(file_path_absolute)
+    if file_path_type == FILE_PATH_TYPE_DIRECTORY:
+        return get_geotiff_files(file_path_absolute)
+    if file_path_type == FILE_PATH_TYPE_FILE:
+        ext = os.path.splitext(file_path_absolute)[1].lower()
+        if ext in FILE_PATH_MAIN_EXTENSIONS:
+            return [file_path_absolute]
+    return []
+
+
+def validate_file_path_source(file_path, file_path_absolute):
+    file_path_type = get_file_path_type(file_path_absolute)
+    if file_path_type == FILE_PATH_TYPE_DIRECTORY:
+        if not (
+                os.access(file_path_absolute, os.R_OK)
+                and os.access(file_path_absolute, os.X_OK)
+        ):
+            raise LaymanError(2, {
+                'parameter': 'file_path',
+                'message': 'Directory is not readable',
+                'expected': 'Readable directory containing raster files',
+                'found': file_path,
+            })
+    elif file_path_type == FILE_PATH_TYPE_FILE:
+        ext = os.path.splitext(file_path_absolute)[1].lower()
+        if ext not in FILE_PATH_MAIN_EXTENSIONS:
+            raise LaymanError(2, {
+                'parameter': 'file_path',
+                'message': 'Path is not a supported raster file',
+                'expected': f'Relative path to GeoTIFF file with extension in {settings.FILE_PATH_MAIN_FILE_EXTENSIONS}',
+                'found': file_path,
+            })
+        if not os.access(file_path_absolute, os.R_OK):
+            raise LaymanError(2, {
+                'parameter': 'file_path',
+                'message': 'Raster file is not readable',
+                'expected': 'Readable GeoTIFF file',
+                'found': file_path,
+            })
+    else:
+        raise LaymanError(2, {
+            'parameter': 'file_path',
+            'message': 'Path is not a directory or file',
+            'expected': 'Relative path to existing directory or GeoTIFF file',
+            'found': file_path,
+        })
+
+    tif_files = get_file_path_geotiff_files(file_path_absolute, file_path_type=file_path_type)
+    if not tif_files:
+        raise LaymanError(2, {
+            'parameter': 'file_path',
+            'message': 'Directory does not contain any raster files',
+            'expected': 'Directory containing at least one GeoTIFF file (.tif or .tiff) or a GeoTIFF file path',
+            'found': file_path,
+        })
+    return file_path_type, tif_files
 
 
 def validate_and_process_file_path(file_path, *, check_crs=True):
@@ -271,7 +340,7 @@ def validate_and_process_file_path(file_path, *, check_crs=True):
         raise LaymanError(2, {
             'parameter': 'file_path',
             'message': 'Absolute path is not allowed',
-            'expected': 'Relative path to directory (relative to GEOSERVER_DATADIR)',
+            'expected': 'Relative path to directory or GeoTIFF file (relative to GEOSERVER_DATADIR)',
             'found': file_path,
         })
 
@@ -282,61 +351,46 @@ def validate_and_process_file_path(file_path, *, check_crs=True):
         raise LaymanError(2, {
             'parameter': 'file_path',
             'message': 'Path is outside GeoServer data directory',
-            'expected': 'Relative path to directory inside GeoServer data directory',
+            'expected': 'Relative path to directory or GeoTIFF file inside GeoServer data directory',
             'found': file_path,
         })
 
     if not os.path.exists(file_path_absolute):
         raise LaymanError(2, {
             'parameter': 'file_path',
-            'message': 'Directory does not exist',
-            'expected': 'Relative path to existing directory on server',
+            'message': 'Path does not exist',
+            'expected': 'Relative path to existing directory or GeoTIFF file on server',
             'found': file_path,
         })
 
-    if not os.path.isdir(file_path_absolute):
-        raise LaymanError(2, {
-            'parameter': 'file_path',
-            'message': 'Path is not a directory',
-            'expected': 'Relative path to existing directory containing raster files',
-            'found': file_path,
-        })
-
-    if not (
-            os.access(file_path_absolute, os.R_OK)
-            and os.access(file_path_absolute, os.X_OK)
-    ):
-        raise LaymanError(2, {
-            'parameter': 'file_path',
-            'message': 'Directory is not readable',
-            'expected': 'Readable directory containing raster files',
-            'found': file_path,
-        })
-
-    tif_files = get_geotiff_files(file_path_absolute)
-    if not tif_files:
-        raise LaymanError(2, {
-            'parameter': 'file_path',
-            'message': 'Directory does not contain any raster files',
-            'expected': 'Directory containing at least one GeoTIFF file (.tif or .tiff)',
-            'found': file_path,
-        })
+    file_path_type, tif_files = validate_file_path_source(file_path, file_path_absolute)
 
     if check_crs:
         for tif_file in tif_files:
             input_file.check_raster_layer_crs(tif_file)
 
-    return file_path, file_path_absolute, None, None
+    return file_path, file_path_absolute, file_path_type, tif_files
+
 
+def validate_file_path_requires_time_regex(file_path_absolute, time_regex, *, file_path_type, tif_files):
+    if file_path_type == FILE_PATH_TYPE_FILE and time_regex:
+        file_path_relative = os.path.relpath(file_path_absolute, settings.GEOSERVER_DATADIR)
+        raise LaymanError(48, {
+            'parameters': ['file_path', 'time_regex'],
+            'message': 'time_regex is not allowed for file_path pointing to a file',
+            'expected': 'Provide file_path to a directory when using time_regex',
+            'found': {
+                'file_path': file_path_relative,
+                'time_regex': time_regex,
+            },
+        })
 
-def validate_file_path_requires_time_regex(file_path_absolute, time_regex):
-    tif_files = get_geotiff_files(file_path_absolute)
-    if len(tif_files) > 1 and not time_regex:
+    if file_path_type == FILE_PATH_TYPE_DIRECTORY and len(tif_files) > 1 and not time_regex:
         file_path_relative = os.path.relpath(file_path_absolute, settings.GEOSERVER_DATADIR)
         raise LaymanError(48, {
             'parameters': ['file_path', 'time_regex'],
             'message': 'Directory contains multiple raster files, but time_regex is not provided',
-            'expected': 'Provide time_regex parameter for image mosaic when directory contains multiple raster files',
+            'expected': 'Provide time_regex for image mosaic or specify file_path to a single raster file',
             'found': {
                 'file_path': file_path_relative,
                 'raster_files_count': len(tif_files),