Merge pull request #181 from yueqixuan/main

Update

Author: ypriverol

docs/DIANN/multiqc_report.html

@@ -4,15 +4,14 @@
 import shutil
 import time
 import urllib
-import zipfile
-import gzip
-import tarfile
 from ftplib import FTP
 from pathlib import Path
 from urllib.parse import urlparse
 
 from tqdm import tqdm
 
+from pmultiqc.modules.common.file_utils import extract_files
+
 
 def download_file(url, save_path, max_retries=3, backoff_factor=2):
     parsed_url = urlparse(url)
@@ -84,46 +83,6 @@ def reporthook(block_num, block_size, total_size):
                 raise http_err
 
 
-def extract_zip(file_path, extract_to):
-    with zipfile.ZipFile(file_path, "r") as zip_ref:
-        zip_ref.extractall(extract_to)
-        print(f"Extracted {file_path} to {extract_to}")
-
-
-def extract_gz(file_path, extract_to):
-    with gzip.open(file_path, "rb") as f_in:
-        out_path = os.path.join(extract_to, os.path.basename(file_path).replace(".gz", ""))
-        with open(out_path, "wb") as f_out:
-            shutil.copyfileobj(f_in, f_out)
-            print(f"Extracted {file_path} to {out_path}")
-
-
-def extract_tar(file_path, extract_to):
-    with tarfile.open(file_path, "r:*") as tar_ref:
-        tar_ref.extractall(extract_to)
-        print(f"Extracted {file_path} to {extract_to}")
-
-
-def extract_files(folder_path):
-    for root, _, files in os.walk(folder_path):
-        for file in files:
-            file_path = os.path.join(root, file)
-            # *.zip
-            if file.endswith(".zip"):
-                extract_zip(file_path, root)
-            # *.gz
-            elif file.endswith(".gz") and not file.endswith(".tar.gz"):
-                extract_gz(file_path, root)
-            # .tar, .tar.gz, .tar.bz2
-            elif (
-                file.endswith(".tar")
-                or file.endswith(".tar.gz")
-                or file.endswith(".tgz")
-                or file.endswith(".tar.bz2")
-            ):
-                extract_tar(file_path, root)
-
-
 def delete_old_examples(folder_path):
     for filename in os.listdir(folder_path):
         file_path = os.path.join(folder_path, filename)

docs/LFQ_PXD007683/multiqc_report.html

@@ -4,7 +4,7 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - multiqc==1.26
+  - multiqc==1.29
   - pandas<=2.0.3
   - pyteomics
   - pyopenms

docs/PXD003133/multiqc_report.html

@@ -8,6 +8,10 @@
 import logging
 from multiqc import config
 
+from pathlib import Path
+import os
+from pmultiqc.modules.common.file_utils import is_archive_file, extract_archive_file, get_clean_stem
+
 # Initialise the main MultiQC logger
 log = logging.getLogger("pmultiqc")
 
@@ -30,21 +34,32 @@ def pmultiqc_plugin_execution_start():
 
     log.warning("Running pmultiqc Plugin v{}".format(config.pmultiqc_version))
 
+    # If a compressed file is submitted, extract it first.
+    analysis_dir_new = list()
+    for anal_dir in config.analysis_dir:
+        if is_archive_file(anal_dir):
+
+            root = Path(anal_dir).parent
+            file = Path(anal_dir).name
+            extract_archive_file(root, file)
+
+            output_dir = os.path.join(root, get_clean_stem(anal_dir))
+
+            if os.path.exists(output_dir):
+                analysis_dir_new.append(output_dir)
+            else:
+                raise SystemExit(f"Illegal file path: {output_dir}")
+        else:
+            analysis_dir_new.append(anal_dir)
+    config.analysis_dir = analysis_dir_new
+    
+    # Module filename search patterns
     if "quantms/exp_design" not in config.sp:
-        config.update_dict(
-            config.sp,
-            {
-                "quantms/exp_design": {"fn": "experimental_design.tsv", "num_lines": 0},
-                "shared": False,
-            },
-        )
+        config.update_dict(config.sp, {"quantms/exp_design": {"fn": "experimental_design.tsv", "num_lines": 0}})
 
     if "quantms/sdrf" not in config.sp:
-        config.update_dict(
-            config.sp, {"quantms/sdrf": {"fn": "*.sdrf.tsv", "num_lines": 0}, "shared": False}
-        )
+        config.update_dict(config.sp, {"quantms/sdrf": {"fn": "*.sdrf.tsv", "num_lines": 0}})
 
-    # Add to the search patterns used by modules
     if "quantms/mztab" not in config.sp:
         config.update_dict(config.sp, {"quantms/mztab": {"fn": "*.mzTab", "num_lines": 0}})
 
@@ -58,24 +73,16 @@ def pmultiqc_plugin_execution_start():
         config.update_dict(config.sp, {"quantms/mzid": {"fn": "*.mzid", "num_lines": 0}})
 
     if "quantms/ms_info" not in config.sp:
-        config.update_dict(
-            config.sp, {"quantms/ms_info": {"fn": "*_ms_info.parquet", "num_lines": 0}}
-        )
+        config.update_dict(config.sp, {"quantms/ms_info": {"fn": "*_ms_info.parquet", "num_lines": 0}})
 
     if "quantms/idXML" not in config.sp:
         config.update_dict(config.sp, {"quantms/idXML": {"fn": "*.idXML", "num_lines": 0}})
 
     if "quantms/msstats" not in config.sp:
-        config.update_dict(
-            config.sp, {"quantms/msstats": {"fn": "*msstats_in.csv", "num_lines": 0}}
-        )
+        config.update_dict(config.sp, {"quantms/msstats": {"fn": "*msstats_in.csv", "num_lines": 0}})
 
     if "quantms/diann_report" not in config.sp:
-        # TODO Why is the 'shared' suddenly inside the dict???
-        config.update_dict(
-            config.sp,
-            {"quantms/diann_report": {"fn": "*report.tsv", "num_lines": 0, "shared": False}},
-        )
+        config.update_dict(config.sp, {"quantms/diann_report": {"fn": "*report.tsv", "num_lines": 0}})
 
     if "quantms/maxquant_result" not in config.sp:
         config.update_dict(config.sp, {"quantms/maxquant_result": {"fn": "*.txt", "num_lines": 0}})