inscriptis 2.5.3__tar.gz → 2.6.0__tar.gz

{inscriptis-2.5.3 → inscriptis-2.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: inscriptis
-Version: 2.5.3
+Version: 2.6.0
 Summary: inscriptis - HTML to text converter.
 Home-page: https://github.com/weblyzard/inscriptis
 License: Apache-2.0
@@ -21,10 +21,10 @@ Classifier: Topic :: Text Processing
 Classifier: Topic :: Text Processing :: Markup :: HTML
 Classifier: Topic :: Utilities
 Provides-Extra: web-service
-Requires-Dist: fastapi (>=0.109.1,<0.110.0) ; extra == "web-service"
+Requires-Dist: fastapi (>=0.115.11,<0.116.0) ; extra == "web-service"
 Requires-Dist: lxml (>=4.9.3)
 Requires-Dist: requests (>=2.32.2)
-Requires-Dist: uvicorn (>=0.27.1,<0.28.0) ; extra == "web-service"
+Requires-Dist: uvicorn (>=0.34.0,<0.35.0) ; extra == "web-service"
 Project-URL: Documentation, https://inscriptis.readthedocs.io/en
 Project-URL: Repository, https://github.com/weblyzard/inscriptis
 Description-Content-Type: text/x-rst
@@ -267,7 +267,7 @@ that are suitable for your particular application. Post processors can be
 specified with the ``-p`` or ``--postprocessor`` command line argument::
 
   $ inscript https://www.fhgr.ch \
-          -r ./annotation/examples/annotation-profile.json \
+          -r ./examples/annotation/annotation-profile.json \
           -p surface
 
 
@@ -296,10 +296,12 @@ Currently, inscriptis supports the following postprocessors:
 - xml: returns an additional annotated text version::
 
     <?xml version="1.0" encoding="UTF-8" ?>
+    <content>
     <heading>Chur</heading>
 
     <emphasis>Chur</emphasis> is the capital and largest town of the Swiss
     canton of the Grisons and lies in the Grisonian Rhine Valley.
+    </content>
 
 - html: creates an HTML file which contains the converted text and highlights all annotations as outlined below:
 
@@ -313,7 +315,7 @@ Currently, inscriptis supports the following postprocessors:
 
       inscript --annotation-rules ./wikipedia.json \
                   --postprocessor html \
-                  https://en.wikipedia.org/wiki/Chur.html
+                  https://en.wikipedia.org/wiki/Chur
 
    Annotation rules encoded in the ``wikipedia.json`` file:
 

{inscriptis-2.5.3 → inscriptis-2.6.0}/README.rst

@@ -236,7 +236,7 @@ that are suitable for your particular application. Post processors can be
 specified with the ``-p`` or ``--postprocessor`` command line argument::
 
   $ inscript https://www.fhgr.ch \
-          -r ./annotation/examples/annotation-profile.json \
+          -r ./examples/annotation/annotation-profile.json \
           -p surface
 
 
@@ -265,10 +265,12 @@ Currently, inscriptis supports the following postprocessors:
 - xml: returns an additional annotated text version::
 
     <?xml version="1.0" encoding="UTF-8" ?>
+    <content>
     <heading>Chur</heading>
 
     <emphasis>Chur</emphasis> is the capital and largest town of the Swiss
     canton of the Grisons and lies in the Grisonian Rhine Valley.
+    </content>
 
 - html: creates an HTML file which contains the converted text and highlights all annotations as outlined below:
 
@@ -282,7 +284,7 @@ Currently, inscriptis supports the following postprocessors:
 
       inscript --annotation-rules ./wikipedia.json \
                   --postprocessor html \
-                  https://en.wikipedia.org/wiki/Chur.html
+                  https://en.wikipedia.org/wiki/Chur
 
    Annotation rules encoded in the ``wikipedia.json`` file:
 

{inscriptis-2.5.3 → inscriptis-2.6.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "inscriptis"
-version = "2.5.3"
+version = "2.6.0"
 authors = ["Albert Weichselbraun <albert.weichselbraun@fhgr.ch>", "Fabian Odoni <fabian.odoni@fhgr.ch>"]
 description = "inscriptis - HTML to text converter."
 keywords = ["HTML", "converter", "text"]
@@ -44,8 +44,11 @@ requests = ">=2.32.2"
 lxml = ">=4.9.3"
 
 # optional dependencies
-fastapi = { version = "^0.109.1", optional = true }
-uvicorn = { version = "^0.27.1", optional = true }
+fastapi = { version = "^0.115.11", optional = true }
+uvicorn = { version = "^0.34.0", optional = true }
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^8.3.5"
 
 
 [build-system]

{inscriptis-2.5.3 → inscriptis-2.6.0}/src/inscriptis/annotation/output/__init__.py

@@ -10,9 +10,9 @@ by overwrite the class's :meth:`AnnotationProcessor.__call__` method.
     2. The overwritten :meth:`__call__` method may either extend the original
        dictionary which contains the extracted text and annotations (e.g.,
        :class:`~inscriptis.annotation.output.surface.SurfaceExtractor`) or
-       may replace it with an custom output (e.g.,
+       may replace it with a custom output (e.g.,
        :class:`~inscriptis.annotation.output.html.HtmlExtractor` and
-       :class:`~inscriptis.annotation.output.xml.XmlExtractor`.
+       :class:`~inscriptis.annotation.output.xml.XmlExtractor`).
 
 Currently, Inscriptis supports the following built-in AnnotationProcessors:
 
@@ -25,6 +25,7 @@ Currently, Inscriptis supports the following built-in AnnotationProcessors:
     of the extracted annotations.
 
 """
+
 from typing import Dict, Any
 
 

{inscriptis-2.5.3 → inscriptis-2.6.0}/src/inscriptis/annotation/output/html.py

@@ -1,4 +1,5 @@
 """HTML Annotation Processor."""
+
 from collections import defaultdict
 from itertools import cycle
 from typing import Dict, Any, List
@@ -18,44 +19,27 @@ class HtmlExtractor(AnnotationProcessor):
     verbatim = True
 
     def __call__(self, annotated_text: Dict[str, Any]) -> str:
-        tag_indices = defaultdict(list)
+        tag_dict = defaultdict(list)
 
-        for start, end, label in sorted(annotated_text["label"]):
-            tag_indices[start].append(label)
-            tag_indices[end].append("/" + label)
+        for start, end, label in reversed(annotated_text["label"]):
+            tag_dict[start].append(
+                f'<span class="{label}-label">{label}</span><span class="{label}">'
+            )
+            tag_dict[end].insert(0, "</span>")
 
-        open_tags = []
         tagged_content = [
             "<html><head><style>",
             self._get_css(annotated_text["label"]),
             "</style></head><body><pre>",
         ]
-        for idx, ch in enumerate(annotated_text["text"]):
-            if idx in tag_indices:
-                tags = tag_indices[idx]
-                # close tags:
-                for _ in (t for t in sorted(tags, reverse=True) if t.startswith("/")):
-                    open_tags.pop()
-                    tagged_content.append("</span>")
-                # open tags
-                for tag in (
-                    t for t in sorted(tags, reverse=True) if not t.startswith("/")
-                ):
-                    open_tags.append(tag)
-                    tagged_content.append(
-                        '<span class="{tag}-label">{tag}</span>'
-                        '<span class="{tag}">'.format(tag=tag)
-                    )
-
-            if ch == "\n":
-                tagged_content.extend(["</span>" for _ in open_tags])
-                tagged_content.append("</pre>\n<pre>")
-                tagged_content.extend(
-                    ['<span class="{tag}">'.format(tag=tag) for tag in open_tags]
-                )
-            else:
-                tagged_content.append(ch)
 
+        text = annotated_text["text"]
+        current_idx = 0
+        for idx, tags in sorted(tag_dict.items()):
+            tagged_content.append(text[current_idx:idx].replace("\n", "</pre>\n<pre>"))
+            current_idx = idx
+            tagged_content.extend(tags)
+        tagged_content.append(text[current_idx:].replace("\n", "</pre>\n</pre>"))
         return "".join(tagged_content) + "</pre></body></html>"
 
     @staticmethod

inscriptis-2.6.0/src/inscriptis/annotation/output/xml.py

@@ -0,0 +1,30 @@
+"""XML Annotation processor."""
+
+from collections import defaultdict
+from typing import Dict, Any
+
+from inscriptis.annotation.output import AnnotationProcessor
+
+
+class XmlExtractor(AnnotationProcessor):
+    """Provide the converted text with XML-style annotations."""
+
+    verbatim = True
+
+    def __call__(self, annotated_text: Dict[str, Any], root_element="content"):
+        tag_dict = defaultdict(list)
+        for start, end, tag in reversed(annotated_text["label"]):
+            tag_dict[start].append(f"<{tag}>")
+            tag_dict[end].insert(0, f"</{tag}>")
+
+        current_idx = 0
+        text = annotated_text["text"]
+        tagged_content = ['<?xml version="1.0" encoding="UTF-8" ?>\n', "<content>\n"]
+        for idx, tags in sorted(tag_dict.items()):
+            tagged_content.append(text[current_idx:idx])
+            current_idx = idx
+            tagged_content.extend(tags)
+
+        tagged_content.append(text[current_idx:])
+        tagged_content.append("\n</content>")
+        return "".join(tagged_content)

{inscriptis-2.5.3 → inscriptis-2.6.0}/src/inscriptis/html_engine.py

@@ -51,7 +51,9 @@ class Inscriptis:
       text = parser.get_text()
     """
 
-    def __init__(self, html_tree: lxml.html.HtmlElement, config: ParserConfig = None):
+    def __init__(
+        self, html_tree: lxml.html.HtmlElement, config: ParserConfig = None
+    ) -> None:
         # use the default configuration, if no config object is provided
         config = config or ParserConfig()
 

inscriptis-2.5.3/src/inscriptis/annotation/output/xml.py

@@ -1,49 +0,0 @@
-"""XML Annotation processor."""
-from collections import defaultdict
-from typing import Dict, Any
-
-from inscriptis.annotation.output import AnnotationProcessor
-
-
-class XmlExtractor(AnnotationProcessor):
-    """Provide the converted text with XML-style annotations."""
-
-    verbatim = True
-
-    def __call__(self, annotated_text: Dict[str, Any]) -> str:
-        """Provide an XML version of the given text and annotations.
-
-        Args:
-            annotated_text: a dictionary containing the plain text and the
-                            extracted annotations.
-
-        Returns:
-            A string with the XML-version of the content.
-        """
-        tag_indices = defaultdict(list)
-
-        for start, end, label in sorted(annotated_text["label"]):
-            tag_indices[start].append(label)
-            tag_indices[end].append("/" + label)
-
-        current_idx = 0
-        tagged_content = ['<?xml version="1.0" encoding="UTF-8" ?>\n']
-        text = annotated_text["text"]
-        for index, tags in sorted(tag_indices.items()):
-            tagged_content.append(text[current_idx:index])
-            # close tags
-            tagged_content.extend(
-                [
-                    "<" + tag + ">"
-                    for tag in sorted(tags, reverse=True)
-                    if tag.startswith("/")
-                ]
-            )
-            # open tags
-            tagged_content.extend(
-                ["<" + tag + ">" for tag in sorted(tags) if not tag.startswith("/")]
-            )
-            current_idx = index
-        tagged_content.append(text[current_idx:])
-
-        return "".join(tagged_content)