lido receives new command line option to disable rescaning lvl1 files…

… as prepration of relWorksCache

zml2lido/__init__.py

@@ -67,6 +67,13 @@ def lido():
         required=False,
         action="store_true",
     )
+    parser.add_argument(
+        "-d",
+        "--disablerescan",
+        action="store_true",
+        default=False,
+        help="set to disable rescanning available lvl1 lido files to pre-populate relWorksCache",
+    )
     parser.add_argument("-i", "--input", help="zml input file", required=True)
     parser.add_argument("-j", "--job", help="pick job (e.g. smb or dd)", required=True)
     parser.add_argument(
@@ -80,8 +87,18 @@ def lido():
 
     print(f"JOB: {args.job}")
 
+    if args.disablerescan is True:
+        print(f"rescan is off (False)")
+        rescan = False
+    else:
+        rescan = True
+
     lt = LidoTool(
-        src=args.input, force=args.force, validation=args.validate, chunks=args.chunks
+        src=args.input,
+        force=args.force,
+        validation=args.validate,
+        chunks=args.chunks,
+        rescan=rescan,
     )
     lt.execute(args.job)
 

zml2lido/lidoTool.py

@@ -63,6 +63,7 @@ def __init__(
         force: bool = False,
         validation: bool = False,
         chunks: bool = False,
+        rescan: bool = True,
     ) -> None:
         """
         src: lido file or first chunk
@@ -75,7 +76,7 @@ def __init__(
         self.force = force
         self.chunks = chunks
         self.script_dir = Path(__file__).parents[1]
-
+        self.rescan = rescan
         self.src = self._sanitize(src=src)  # returns Path
         self.outdir = self._prepareOutdir()
         print(f" outdir {self.outdir}")
@@ -143,7 +144,9 @@ def to_lvl2_single(self, *, src: Path) -> Path:
         except AttributeError:
             # only initalize and load lido files into relWorksCache once
             # need src here for path atm
-            self.lc = LinkChecker(src=src, chunks=self.chunks)
+            self.lc = LinkChecker(
+                src=src, chunks=self.chunks, rescan_lvl1_at_init=self.rescan
+            )
         out_fn = self._lvl2_path(src)
         if not out_fn.exists() or self.force:
             self.lc.load_lvl1(src=src)

zml2lido/linkChecker.py

@@ -30,11 +30,11 @@
 # from zml2lido import NSMAP
 NSMAP = {"l": "http://www.lido-schema.org"}
 
-rescan_lvl1_files_at_init = False
-
 
 class LinkChecker:
-    def __init__(self, *, src: Path, chunks: bool = False) -> None:
+    def __init__(
+        self, *, src: Path, chunks: bool = False, rescan_lvl1_at_init: bool = True
+    ) -> None:
         logging.debug(
             f"STATUS: LinkChecker is working on {src}"
         )  # not exactly an error
@@ -46,7 +46,7 @@ def __init__(self, *, src: Path, chunks: bool = False) -> None:
         self.rwc = RelWorksCache(maxSize=20_000, cache_dir=cache_dir)
         self.rwc.load_cache_file()  # load file if it exists once atb
 
-        if rescan_lvl1_files_at_init:
+        if rescan_lvl1_at_init:
             # run only once to update cache
             if self.chunks:
                 print("prepare relWorks cache (chunks, many)")
@@ -108,7 +108,7 @@ def fixRelatedWorks(self) -> None:
                     print(
                         f"{idx}/{len(relatedWorksL)}{objectID_N.text} already rewritten"
                     )
-            if idx % 100:
+            if idx % 100 == 0:
                 self.rwc.save_if_changed()
 
     def linkResource_online_http(self) -> None: