ccfx 0.5.0__py3-none-any.whl → 0.7.0__py3-none-any.whl

ccfx/ccfx.py

@@ -29,7 +29,10 @@ import subprocess
 import multiprocessing
 from mutagen.mp3 import MP3
 from mutagen.id3 import ID3, TPE1, TALB, TIT2, TRCK, TDRC, TCON, APIC, COMM, USLT, TPE2, TCOM, TPE3, TPE4, TCOP, TENC, TSRC, TBPM
-
+from concurrent.futures import ThreadPoolExecutor
+import math
+import requests
+from tqdm import tqdm
 
 # functions
 def listFiles(path: str, ext: str = None) -> list:
@@ -247,6 +250,82 @@ def deletePath(path:str, v:bool = False) -> bool:
         deleted = False
 
 
+def downloadChunk(url, start, end, path):
+    headers = {'Range': f'bytes={start}-{end}'}
+    response = requests.get(url, headers=headers, stream=True)
+    with open(path, 'wb') as f:
+        for chunk in response.iter_content(chunk_size=8192):
+            if chunk:
+                f.write(chunk)
+
+def downloadFile(url, save_path, exists_action='resume', num_connections=5, v=True):
+    if v:
+        print(f"\ndownloading {url}")
+    fname = getFileBaseName(url, extension=True)
+    save_dir = os.path.dirname(save_path)
+    save_fname = "{0}/{1}".format(save_dir, fname)
+
+    if not os.path.isdir(save_dir):
+        os.makedirs(save_dir)
+
+    # Handle existing file
+    if os.path.exists(save_fname):
+        if exists_action == 'skip':
+            if v:
+                print(f"File exists, skipping: {save_fname}")
+            return
+        elif exists_action == 'overwrite':
+            os.remove(save_fname)
+        # 'resume' is handled below
+
+    # Get file size
+    response = requests.head(url)
+    file_size = int(response.headers.get('content-length', 0))
+
+    # Resume download if file exists and exists_action is 'resume'
+    initial_pos = 0
+    if exists_action == 'resume' and os.path.exists(save_fname):
+        initial_pos = os.path.getsize(save_fname)
+        if initial_pos >= file_size:
+            if v:
+                print(f"File already completed: {save_fname}")
+            return
+
+    # Calculate chunk sizes
+    chunk_size = math.ceil((file_size - initial_pos) / num_connections)
+    chunks = []
+    for i in range(num_connections):
+        start = initial_pos + (i * chunk_size)
+        end = min(start + chunk_size - 1, file_size - 1)
+        chunks.append((start, end))
+
+    # Download chunks in parallel
+    temp_files = [f"{save_fname}.part{i}" for i in range(num_connections)]
+    with ThreadPoolExecutor(max_workers=num_connections) as executor:
+        futures = []
+        for i, (start, end) in enumerate(chunks):
+            futures.append(
+                executor.submit(downloadChunk, url, start, end, temp_files[i])
+            )
+        
+        # Wait for all downloads to complete with progress bar
+        with tqdm(total=file_size-initial_pos, initial=initial_pos, unit='B', 
+                 unit_scale=True, desc=fname) as pbar:
+            completed = initial_pos
+            while completed < file_size:
+                current = sum(os.path.getsize(f) for f in temp_files if os.path.exists(f))
+                pbar.update(current - completed)
+                completed = current
+
+    # Merge chunks
+    with open(save_fname, 'ab' if initial_pos > 0 else 'wb') as outfile:
+        for temp_file in temp_files:
+            if os.path.exists(temp_file):
+                with open(temp_file, 'rb') as infile:
+                    outfile.write(infile.read())
+                os.remove(temp_file)
+
+
 def mergeRasterTiles(tileList:list, outFile:str) -> str:
     '''
     Merge raster tiles into one raster file
@@ -1114,6 +1193,29 @@ def listAllFiles(folder, extension="*"):
     return list_of_files
 
 
+def clipFeatures(inputFeaturePath:str, boundaryFeature:str, outputFeature:str, keepOnlyTypes = None, v = False) -> geopandas.GeoDataFrame:
+    '''
+    keepOnlyTypes = ['MultiPolygon', 'Polygon', 'Point', etc]
+    
+    '''
+    mask_gdf = geopandas.read_file(boundaryFeature)
+    input_gdf = geopandas.read_file(inputFeaturePath)
+
+    outDir = os.path.dirname(outputFeature)
+    createPath(f"{outDir}/")
+    out_gdf = input_gdf.clip(mask_gdf.to_crs(input_gdf.crs))
+
+    if not keepOnlyTypes is None:
+        out_gdf = out_gdf[out_gdf.geometry.apply(lambda x : x.type in keepOnlyTypes)]
+
+    out_gdf.to_file(outputFeature)
+
+    if v:
+        print("\t  - clipped feature to " + outputFeature)
+    return out_gdf
+
+
+
 def createPointGeometry(coords: list, proj: str = "EPSG:4326") -> geopandas.GeoDataFrame:
     '''
     Convert list of coordinate tuples to GeoDataFrame

{ccfx-0.5.0.dist-info → ccfx-0.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ccfx
-Version: 0.5.0
+Version: 0.7.0
 Summary: This package simplifies regular common actions for quick prototyping in a user friendly way
 Author-email: Celray James CHAWANDA <celray@chawanda.com>
 License: MIT
@@ -23,6 +23,8 @@ Requires-Dist: sqlalchemy
 Requires-Dist: python-docx
 Requires-Dist: py7zr
 Requires-Dist: mutagen
+Requires-Dist: requests
+Requires-Dist: tqdm
 Dynamic: license-file
 
 # ccfx

{ccfx-0.5.0.dist-info → ccfx-0.7.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
 ccfx/__init__.py,sha256=VmBeF3oj6JTJ_793d4i8PvhyF8_FxaxA1L_FmHWqitc,142
-ccfx/ccfx.py,sha256=A61uV0bKlusLAcLlgNVhKaMQ4KutWxB7hzEQnitJpus,51808
+ccfx/ccfx.py,sha256=4BD22BQovfkcAFZRkoHaA1quvXlDBFc1GiH_Fffz6Q8,55571
 ccfx/excel.py,sha256=cQ4TQW49XqbMB3sSS0IOhO3-WArIolEBIrvOvhFyPtI,4757
 ccfx/mssqlConnection.py,sha256=TwyZXhHHI7zy6BSfH1pszuHVJ5cmndRC5dVxvEtSTks,7904
 ccfx/sqliteConnection.py,sha256=jEJ94D5ySt84N7AeDpa27Rclt1NaKhkX6nYzidwApIg,11104
 ccfx/word.py,sha256=AGa64jX5Zl5qotZh5L0QmrsjTnktIBhmj_ByRKZ88vw,3061
-ccfx-0.5.0.dist-info/licenses/LICENSE,sha256=2-M3fBUS3FmrSIrqd3cZDmxXxojWVJtZY-SHSRE6RxM,1098
-ccfx-0.5.0.dist-info/METADATA,sha256=6tpyj3FwWBdkm8BCvU26J9rZFsP_mCIoZUxTb71GYRA,5381
-ccfx-0.5.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ccfx-0.5.0.dist-info/top_level.txt,sha256=_cSvSA1WX2K8TgoV3iBJUdUZZqMKJbOPLNnKLYSLHaw,5
-ccfx-0.5.0.dist-info/RECORD,,
+ccfx-0.7.0.dist-info/licenses/LICENSE,sha256=2-M3fBUS3FmrSIrqd3cZDmxXxojWVJtZY-SHSRE6RxM,1098
+ccfx-0.7.0.dist-info/METADATA,sha256=_rPWPy0bHKGdUv5y2Ovt_XGpIbRv7Xa33oJJDfWDv-o,5425
+ccfx-0.7.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ccfx-0.7.0.dist-info/top_level.txt,sha256=_cSvSA1WX2K8TgoV3iBJUdUZZqMKJbOPLNnKLYSLHaw,5
+ccfx-0.7.0.dist-info/RECORD,,