add new xpath tool

pyproject.toml

@@ -24,7 +24,7 @@ lido = 'zml2lido:lido'
 lvalidate = 'zml2lido:validate' 
 saxon = 'zml2lido:saxon'
 vocmap = 'zml2lido:vocmap'
-
+xpath = 'zml2lido:xpath'
 
 [project.urls]
 Home = "https://github.com/mokko/zml2lido"

zml2lido/__init__.py

@@ -12,6 +12,7 @@
 from zml2lido.lidoTool import LidoTool
 from zml2lido.linkChecker import LinkChecker
 from zml2lido.vocmap import Vocmap
+from zml2lido.xpathTool import xpathTool
 
 NSMAP = {"l": "http://www.lido-schema.org"}
 
@@ -157,3 +158,34 @@ def vocmap():
 
     args = parser.parse_args()
     vm = Vocmap(Input=args.Input, output=args.output)
+
+
+def xpath():
+    """ "
+    Little utility that applies xpath expressions to one or multiple files
+    """
+    parser = argparse.ArgumentParser(description="apply xpath to file(s)")
+    parser.add_argument(
+        "-i",
+        "--Input",
+        help="input file or filemask (in case of globbing)",
+        required=True,
+    )
+
+    parser.add_argument(
+        "-f",
+        "--file",
+        help="output to file xpath.xml",
+        action="store_true",
+        default=False,
+    )
+
+    parser.add_argument(
+        "-x",
+        "--xpath",
+        help="the xpath expression",
+        required=True,
+    )
+
+    args = parser.parse_args()
+    xpathTool(Input=args.Input, xpath=args.xpath, file=args.file)

zml2lido/xpathTool.py

@@ -0,0 +1,38 @@
+from lxml import etree
+from pathlib import Path
+
+# NSMAP is already present in linkChecker TODO
+NSMAP = {"l": "http://www.lido-schema.org"}
+
+
+def xpathTool(
+    *, Input: str, xpath: str, file: bool = False, globbing: bool = False
+) -> None:
+    print(f"{Input=}")
+    print(f"{xpath=}")
+    print(f"{file=} (stringify implicit with file option)")
+    out_fn = Path("xpath.xml")
+    if file:
+        if out_fn.exists():
+            out_fn.unlink()
+    for xml_fn in Path(".").glob(Input):
+        print(f"parsing {xml_fn}")
+        tree = etree.parse(xml_fn)
+        resL = tree.xpath(xpath, namespaces=NSMAP)
+        _output(file=file, results=resL, out_fn=out_fn)
+
+
+#
+# somewhat restricted
+#
+
+
+def _output(*, file: bool, results: list, out_fn: Path) -> None:
+    # delete file first then append
+    for resultN in results:
+        if file:  # stringify automatically
+            xml = etree.tostring(resultN, pretty_print=True, encoding="unicode")
+            with open(out_fn, "a") as f:
+                f.write(xml)
+        else:
+            print(resultN)  # not stringified