docs: fix relative links & span_getter args

docs/scripts/plugin.py

@@ -1,10 +1,13 @@
 import os
+import re
 from pathlib import Path
 
 import mkdocs.config
+import mkdocs.plugins
 import mkdocs.structure
 import mkdocs.structure.files
 import mkdocs.structure.nav
+import mkdocs.structure.pages
 
 
 def exclude_file(name):
@@ -118,3 +121,21 @@ def on_page_read_source(page, config):
     if page.file.src_path in VIRTUAL_FILES:
         return VIRTUAL_FILES[page.file.src_path]
     return None
+
+
+@mkdocs.plugins.event_priority(-1000)
+def on_page_content(
+    html: str,
+    page: mkdocs.structure.pages.Page,
+    config: mkdocs.config.Config,
+    files: mkdocs.structure.files.Files,
+):
+    def replace_link(match):
+        relative_url = url = match.group(1)
+        page_url = os.path.join("/", page.file.url)
+        if url.startswith("/"):
+            relative_url = os.path.relpath(url, page_url)
+        return f'href="{relative_url}"'
+
+    # Replace absolute paths with path relative to the rendered page
+    return re.sub(r'href="([^"]*)"', replace_link, html)

edsnlp/pipelines/qualifiers/base.py

@@ -46,8 +46,7 @@ class RuleBasedQualifier(BaseComponent):
         a string with the value "TEXT" or "NORM", or a dict with the key 'term_attr'
         we can also add a key for each regex.
     span_getter : SpanGetterArg
-        Where to look for dates in the doc. By default, look in the whole doc. You can
-        combine this with the `merge_mode` argument for interesting results.
+        Which entities should be classified. By default, `doc.ents`
     on_ents_only : Union[bool, str, List[str], Set[str]]
         Whether to look for matches around detected entities only.
         Useful for faster inference in downstream tasks.

edsnlp/pipelines/qualifiers/family/family.py

@@ -79,8 +79,7 @@ class FamilyContextQualifier(RuleBasedQualifier):
     termination : Optional[List[str]]
         List of syntagms termination terms.
     span_getter : SpanGetterArg
-        Where to look for dates in the doc. By default, look in the whole doc. You can
-        combine this with the `merge_mode` argument for interesting results.
+        Which entities should be classified. By default, `doc.ents`
     on_ents_only : Union[bool, str, List[str], Set[str]]
         Deprecated, use `span_getter` instead.
 

edsnlp/pipelines/qualifiers/history/history.py

@@ -145,8 +145,7 @@ class HistoryQualifier(RuleBasedQualifier):
     closest_dates_only : bool
         Whether to include the closest dates only.
     span_getter : SpanGetterArg
-        Where to look for dates in the doc. By default, look in the whole doc. You can
-        combine this with the `merge_mode` argument for interesting results.
+        Which entities should be classified. By default, `doc.ents`
     on_ents_only : Union[bool, str, List[str], Set[str]]
         Deprecated, use `span_getter` instead.
 

edsnlp/pipelines/qualifiers/hypothesis/hypothesis.py

@@ -115,7 +115,8 @@ class HypothesisQualifier(RuleBasedQualifier):
     attr : str
         spaCy's attribute to use:
         a string with the value "TEXT" or "NORM", or a dict with the key 'term_attr'
-        we can also add a key for each regex.
+    span_getter : SpanGetterArg
+        Which entities should be classified. By default, `doc.ents`
     on_ents_only : Union[bool, str, List[str], Set[str]]
         Deprecated, use `span_getter` instead.
 

edsnlp/pipelines/qualifiers/negation/negation.py

@@ -116,8 +116,7 @@ class NegationQualifier(RuleBasedQualifier):
     termination : Optional[List[str]]
         List of termination terms.
     span_getter : SpanGetterArg
-        Where to look for dates in the doc. By default, look in the whole doc. You can
-        combine this with the `merge_mode` argument for interesting results.
+        Which entities should be classified. By default, `doc.ents`
     on_ents_only : Union[bool, str, List[str], Set[str]]
         Deprecated, use `span_getter` instead.
 

edsnlp/pipelines/qualifiers/reported_speech/reported_speech.py

@@ -83,6 +83,8 @@ class ReportedSpeechQualifier(RuleBasedQualifier):
         a string with the value "TEXT" or "NORM",
         or a dict with the key 'term_attr'
         we can also add a key for each regex.
+    span_getter : SpanGetterArg
+        Which entities should be classified. By default, `doc.ents`
     on_ents_only : Union[bool, str, List[str], Set[str]]
         Whether to look for matches around detected entities only.
         Useful for faster inference in downstream tasks.

mkdocs.yml

@@ -190,7 +190,6 @@ plugins:
             show_root_toc_entry: false
             show_signature: false
             merge_init_into_class: true
-  - autolinks
   - bibtex:
       bibtex_file: "docs/references.bib"
 # Just uncomment the following lines to enable i18n

pyproject.toml

@@ -51,7 +51,6 @@ dev = [
     "mkdocs~=1.5.2",
     "mkdocstrings~=0.20",
     "mkdocstrings-python~=1.1",
-    "mkdocs-autolinks-plugin~=0.7.1",
     "pybtex~=0.24.0",
     "pathspec>=0.11.1",  # required by vendored mkdocs-autorefs PR
     "astunparse",