add new plugin xdxf_css (XdxfCss) based on PR #570 by @soshial

- use CSS for all XDXF element (decrease size of output dict file) - created a list (ol / ul) for nested `<def>`s - support loading of `<abbreviations>` data - show js tooltips for abbreviations - fixed showing hidden `<gr>` - fixed losing spaces before XDXF tags - add braces to `<co>` - show CSS instead of inlined HTML tags for: `<ex>, <pos>, <abbr>, <k>, <gr>, <mrkd>`
ilius · Sep 2, 2024 · aa6765b · aa6765b
1 parent 7f64af5
commit aa6765b
Show file tree

Hide file tree

Showing 8 changed files with 990 additions and 10 deletions.
diff --git a/doc/p/__index__.md b/doc/p/__index__.md
@@ -44,6 +44,7 @@
 | WordNet                        | Wordnet         | [wordnet.md](./wordnet.md)                     |
 | Wordset.org JSON directory     | Wordset         | [wordset.md](./wordset.md)                     |
 | XDXF (.xdxf)                   | Xdxf            | [xdxf.md](./xdxf.md)                           |
+| XDXF with CSS and JS           | XdxfCss         | [xdxf_css.md](./xdxf_css.md)                   |
 | XDXF Lax (.xdxf)               | XdxfLax         | [xdxf_lax.md](./xdxf_lax.md)                   |
 | Yomichan (.zip)                | Yomichan        | [yomichan.md](./yomichan.md)                   |
 | Zim (.zim, for Kiwix)          | Zim             | [zim.md](./zim.md)                             |
diff --git a/doc/p/xdxf_css.md b/doc/p/xdxf_css.md
@@ -0,0 +1,28 @@
+## XDXF with CSS and JS
+
+### General Information
+
+| Attribute       | Value                                                                                                          |
+| --------------- | -------------------------------------------------------------------------------------------------------------- |
+| Name            | XdxfCss                                                                                                        |
+| snake_case_name | xdxf_css                                                                                                       |
+| Description     | XDXF with CSS and JS                                                                                           |
+| Extensions      |                                                                                                                |
+| Read support    | Yes                                                                                                            |
+| Write support   | No                                                                                                             |
+| Single-file     | Yes                                                                                                            |
+| Kind            | 📝 text                                                                                                         |
+| Sort-on-write   | default_no                                                                                                     |
+| Sort key        | (`headword_lower`)                                                                                             |
+| Wiki            | [XDXF](https://en.wikipedia.org/wiki/XDXF)                                                                     |
+| Website         | [XDXF standard - @soshial/xdxf_makedict](https://github.com/soshial/xdxf_makedict/tree/master/format_standard) |
+
+### Dependencies for reading
+
+PyPI Links: [lxml](https://pypi.org/project/lxml)
+
+To install, run:
+
+```sh
+pip3 install lxml
+```
diff --git a/plugins-meta/index.json b/plugins-meta/index.json
@@ -1823,6 +1823,26 @@
 			"lzma"
 		]
 	},
+	{
+		"module": "xdxf_css",
+		"lname": "xdxf_css",
+		"name": "XdxfCss",
+		"description": "XDXF with CSS and JS",
+		"extensions": [],
+		"singleFile": true,
+		"optionsProp": {},
+		"canRead": true,
+		"canWrite": false,
+		"readOptions": {},
+		"readDepends": {
+			"lxml": "lxml"
+		},
+		"readCompressions": [
+			"gz",
+			"bz2",
+			"lzma"
+		]
+	},
 	{
 		"module": "xdxf_lax",
 		"lname": "xdxf_lax",

diff --git a/pyglossary/plugins/xdxf/__init__.py b/pyglossary/plugins/xdxf/__init__.py
@@ -31,6 +31,8 @@
 
 	from pyglossary.lxml_types import Element
 
+from lxml import etree as ET
+
 from pyglossary.compression import (
 	compressionOpen,
 	stdCompressions,
@@ -79,7 +81,6 @@
 	),
 }
 
-
 """
 new format
 <xdxf ...>
@@ -110,9 +111,7 @@
 </xdxf>
 """
 
-
 if TYPE_CHECKING:
-
 	class TransformerType(typing.Protocol):
 		def transform(self, article: "Element") -> str: ...
 
@@ -154,7 +153,6 @@ def makeTransformer(self) -> None:
 
 	def open(self, filename: str) -> None:  # noqa: PLR0912
 		# <!DOCTYPE xdxf SYSTEM "http://xdxf.sourceforge.net/xdxf_lousy.dtd">
-		from lxml import etree as ET
 
 		self._filename = filename
 		if self._html:
@@ -220,9 +218,6 @@ def __len__(self) -> int:
 		return 0
 
 	def __iter__(self) -> "Iterator[EntryType]":
-		from lxml import etree as ET
-		from lxml.etree import tostring
-
 		context = ET.iterparse(  # type: ignore
 			self._file,
 			events=("end",),
@@ -238,7 +233,7 @@ def __iter__(self) -> "Iterator[EntryType]":
 				if len(words) == 1:
 					defi = self._re_span_k.sub("", defi)
 			else:
-				b_defi = cast(bytes, tostring(article, encoding=self._encoding))
+				b_defi = cast(bytes, ET.tostring(article, encoding=self._encoding))
 				defi = b_defi[4:-5].decode(self._encoding).strip()
 				defiFormat = "x"
 
@@ -265,8 +260,6 @@ def close(self) -> None:
 	def tostring(
 		elem: "Element",
 	) -> str:
-		from lxml import etree as ET
-
 		return (
 			ET.tostring(
 				elem,