don't delete project, only remove large files.

jass/__main__.py

@@ -2,7 +2,6 @@
 # -*- coding: utf-8 -*-
 
 import os
-import shutil
 import sys
 import argparse
 from datetime import timedelta, datetime
@@ -14,7 +13,7 @@ from jass.config import config
 from jass.models.phenotype import get_available_phenotypes
 from jass.models.inittable import create_inittable_file, add_gene_annotation
 from jass.models.worktable import create_worktable_file
-from jass.models.project import get_projects_last_access
+from jass.models.project import get_projects_last_access, load_project
 from jass.models.plots import (
     create_global_plot,
     create_quadrant_plot,
@@ -172,8 +171,8 @@ def w_clean_project_data(args):
     for proj in get_projects_last_access():
         print(f"Project {proj['project_id']} was last accessed on {proj['last_access']}, ", end='')
         if proj['last_access'] + shift < datetime.now():
-            print("removing it")
-            shutil.rmtree(proj['path'])
+            print("removing its large files")
+            load_project(project_id=proj['project_id'], flag_as_visited=False).delete_large_files()
         else:
             print("keeping it")
 
@@ -346,13 +345,13 @@ def get_parser():
 
     parser_clean_pd = subparsers.add_parser(
         "clean-project-data",
-        help="Remove old projects that haven't been accessed recently",
+        help="Remove old projects data that haven't been accessed recently",
     )
     parser_clean_pd.add_argument(
         "--max-days-without-access",
         type=int,
         default=30,
-        help="A project is marked for deletion if the number of days elapsed since "
+        help="A project is marked for large file deletion if the number of days elapsed since "
              "the last access is greater than the amount provided.",
     )
     parser_clean_pd.set_defaults(func=w_clean_project_data)

jass/models/project.py

@@ -38,6 +38,7 @@ from jass.models.worktable import (
     get_worktable_phenolist,
     create_worktable_file,
     create_genome_full_csv,
+    create_genome_full_csv_lock_file,
 )
 
 from jass.config import config
@@ -220,6 +221,27 @@ class Project(BaseModel, abc.ABC):
     def create_worktable_file(self):
         pass
 
+    def delete_large_files(self):
+        # delete the worktable file
+        project_hdf_path = self.get_worktable_path()
+        if os.path.exists(project_hdf_path):
+            os.remove(project_hdf_path)
+        # as a consequence, its creation will have to be redone, so set progress to 0 and remove is status.
+        self.progress = 0
+        try:
+            del self.status['worktable']
+        except KeyError:
+            # worktable not in status
+            pass
+        self.save()
+
+        if self.delayed_gen_csv_file:
+            # Delete the full csv file if it exists, and re-set the lock file indicating that it should be generated
+            create_genome_full_csv_lock_file(project_hdf_path)
+            csv_path = self.get_csv_path()
+            if os.path.exists(csv_path):
+                os.remove(csv_path)
+
     @call_with_tb('global_manhattan')
     def create_global_manhattan_plot(self):
         return create_global_plot(
@@ -301,7 +323,7 @@ class LocalProject(Project):
         )
 
 
-def load_project(project_id):
+def load_project(project_id, flag_as_visited: bool = True):
     path = os.path.join(Project.get_folder_path_from_id(project_id), "meta.json")
     with open(path, "r") as fp:
         project = parse_raw_as(
@@ -311,7 +333,8 @@ def load_project(project_id):
             ],
             "".join(fp.readlines()),
         )
-        flag_project_as_visited(project_id)
+        if flag_as_visited:
+            flag_project_as_visited(project_id)
         return project
 
 

jass/models/worktable.py

@@ -394,14 +394,7 @@ def create_worktable_file(
             os.remove(csv_file)
 
         if delayed_gen_csv_file:
-            # setting a lock to generate the csv_file asynchronously
-            the_lock_path = os.path.join(
-                os.path.dirname(project_hdf_path), "the_lock.txt"
-            )
-            the_lock = "The lock is set on : workTable.csv is not yet available"
-            file_lock = open(the_lock_path, "w")
-            file_lock.write(the_lock)
-            file_lock.close()
+            create_genome_full_csv_lock_file(project_hdf_path)
 
     # subset of phenotypes that have been selected
     phenolist = read_hdf(init_file_path, "PhenoList")
@@ -1023,7 +1016,7 @@ def create_genome_full_csv(project_hdf_path, csv_file, chunk_size=50, Nchunk=35)
     """
 
     # path of the lock that indicates that the csv file is not available
-    the_lock_path = os.path.join(os.path.dirname(project_hdf_path), "the_lock.txt")
+    the_lock_path = get_genome_full_csv_lock_path(project_hdf_path)
     if os.path.isfile(the_lock_path):
         # The lock is set on
         if os.path.isfile(csv_file):
@@ -1056,3 +1049,17 @@ def create_genome_full_csv(project_hdf_path, csv_file, chunk_size=50, Nchunk=35)
         The_file_is_available = False
 
     return The_file_is_available
+
+
+def get_genome_full_csv_lock_path(project_hdf_path):
+    the_lock_path = os.path.join(os.path.dirname(project_hdf_path), "the_lock.txt")
+    return the_lock_path
+
+
+def create_genome_full_csv_lock_file(project_hdf_path):
+    # setting a lock to generate the csv_file asynchronously
+    the_lock_path = get_genome_full_csv_lock_path(project_hdf_path)
+    the_lock = "The lock is set on : workTable.csv is not yet available"
+    file_lock = open(the_lock_path, "w")
+    file_lock.write(the_lock)
+    file_lock.close()
\ No newline at end of file