html2docx - pypi Package Compare versions

Comparing version 1.5.0 to 1.6.0

tests/data/table.html

+<table><tr><td>1</td><td><b>2</b></td></tr><tr><td>3</td></tr></table>

tests/data/table.json

+[
+    {
+        "table": [
+            [{
+                "cell": [{
+                    "text":  "1",
+                    "runs": [{ "text":  "1" }]
+                }]
+            },
+            {
+                "cell": [{
+                    "text": "2",
+                    "runs": [{ "text":  "2", "bold": true}]
+                }]
+            }],
+            [{
+                "cell": [{
+                    "text":  "3",
+                    "runs": [{ "text":  "3" }]
+                }]
+            },
+            {
+                "cell": [{
+                    "text":  "",
+                    "runs": []
+                }]
+            }]
+        ]
+    }
+]

html2docx.egg-info/PKG-INFO

 Metadata-Version: 2.1
 Name: html2docx
-Version: 1.5.0
+Version: 1.6.0
 Summary: Convert valid HTML input to docx.
@@ -5,0 +5,0 @@ Home-page: https://github.com/erezlife/html2docx

html2docx.egg-info/SOURCES.txt

@@ -104,2 +104,4 @@ LICENSE
 tests/data/sup.json
+tests/data/table.html
+tests/data/table.json
 tests/data/underline-strikethrough.html
@@ -106,0 +108,0 @@ tests/data/underline-strikethrough.json

html2docx/html2docx.py

@@ -8,2 +8,3 @@ import re
 from docx.shared import Pt
+from docx.table import Table
 from docx.text.paragraph import Paragraph
@@ -82,2 +83,3 @@ from docx.text.run import Run
         self.pre = False
+        self.table: Optional[Tuple[Table, int, int]] = None
         self.alignment: Optional[int] = None
@@ -106,2 +108,33 @@ self.padding_left: Optional[Pt] = None
 
+    def init_table(self, attrs: List[Tuple[str, Optional[str]]]) -> None:
+        self.table = (self.doc.add_table(rows=0, cols=0), -1, -1)
+
+    def finish_table(self) -> None:
+        if self.table is None:
+            return
+        section = self.doc.sections[0]
+        page_width = section.page_width - section.left_margin - section.right_margin
+        table = self.table[0]
+        for col in table.columns:
+            col.width = page_width // len(table.columns)
+        self.table = None
+
+    def init_tr(self) -> None:
+        if self.table is None:
+            return
+        table, row, col = self.table
+        table.add_row()
+        self.table = table, row + 1, -1
+
+    def init_tdth(self) -> None:
+        if self.table is None:
+            return
+        table, row, col = self.table
+        col += 1
+        self.table = (table, row, col)
+        if col >= len(table.columns):
+            table.add_column(0)
+        self.p = self.table[0].cell(row, col).paragraphs[0]
+        self.r = None
+
     def init_run(self, attrs: List[Tuple[str, Any]]) -> None:
@@ -201,2 +234,8 @@ self.attrs.append(attrs)
             self.add_list_style("List Bullet")
+        elif tag == "table":
+            self.init_table(attrs)
+        elif tag == "tr":
+            self.init_tr()
+        elif tag in ["td", "th"]:
+            self.init_tdth()
 
@@ -229,1 +268,6 @@ def handle_data(self, data: str) -> None:
                 self.pre = False
+        elif tag == "table":
+            self.finish_table()
+        elif tag in ["td", "th"]:
+            self.p = None
+            self.r = None

PKG-INFO

 Metadata-Version: 2.1
 Name: html2docx
-Version: 1.5.0
+Version: 1.6.0
 Summary: Convert valid HTML input to docx.
@@ -5,0 +5,0 @@ Home-page: https://github.com/erezlife/html2docx

pyproject.toml

 [build-system]
-requires = [
-    "setuptools>=42",
-    "wheel",
-]
-build-backend = "setuptools.build_meta:__legacy__"
+requires = ["setuptools>=42"]
+build-backend = "setuptools.build_meta"

setup.cfg

 [metadata]
 name = html2docx
-version = 1.5.0
+version = 1.6.0
 url = https://github.com/erezlife/html2docx
@@ -5,0 +5,0 @@ author = eRezLife

tests/test_html2docx.py

 import json
+from typing import Union
 
 import docx
 import pytest
+from docx.document import Document
+from docx.oxml import CT_P, CT_Tbl
 from docx.shared import Pt
+from docx.table import Table, _Cell
+from docx.text.paragraph import Paragraph
 
@@ -29,2 +34,80 @@ from html2docx import html2docx
 
+def get_document_children(element: Union[Document, _Cell]):
+    if isinstance(element, Document):
+        parent_element = element.element.body
+    elif isinstance(element, _Cell):
+        parent_element = element._tc
+    else:
+        raise Exception("Received an item that does not have children.")
+    for child in parent_element.iterchildren():
+        if isinstance(child, CT_P):
+            yield Paragraph(child, element)
+        elif isinstance(child, CT_Tbl):
+            yield Table(child, element)
+
+
+def assert_paragraph_comply_with_spec(
+    p: Paragraph, p_spec: dict, html_rel_path: str, spec_rel_path: str
+):
+    assert p.text == p_spec["text"]
+    assert p.style.name == p_spec.get("style", "Normal")
+    if p_spec.get("alignment") is not None:
+        assert p.alignment == p_spec["alignment"]
+    else:
+        assert p.alignment is None
+    if p_spec.get("left_indent"):
+        assert p.paragraph_format.left_indent == Pt(p_spec["left_indent"])
+    else:
+        assert p.paragraph_format.left_indent is None
+
+    runs_spec = p_spec["runs"]
+    assert len(p.runs) == len(runs_spec)
+    for run, run_spec in zip(p.runs, runs_spec):
+        assert run.text == run_spec.pop("text")
+        shapes_spec = run_spec.pop("shapes", None)
+        unknown = set(run_spec).difference(FONT_ATTRS)
+        assert not unknown, "Unknown attributes in {}: {}".format(
+            spec_rel_path, ", ".join(unknown)
+        )
+        for attr in FONT_ATTRS:
+            msg = f"Wrong {attr} for text '{run.text}' in {html_rel_path}"
+            assert getattr(run.font, attr) == run_spec.get(attr), msg
+        if shapes_spec:
+            shapes = run.part.inline_shapes
+            assert len(shapes) == len(shapes_spec)
+            for shape, shape_spec in zip(shapes, shapes_spec):
+                assert shape.type == shape_spec["type"]
+                assert shape.width == shape_spec["width"]
+                assert shape.height == shape_spec["height"]
+
+
+def assert_table_comply_with_spec(
+    t: Table, t_spec: dict, html_rel_path: str, spec_rel_path: str
+):
+    assert "table" in t_spec
+    assert len(t.rows) == len(t_spec["table"])
+    for (row, row_spec) in zip(t.rows, t_spec["table"]):
+        assert len(t.columns) == len(row_spec)
+        for (cell, cell_spec) in zip(row.cells, row_spec):
+            assert_element_comply_with_spec(
+                cell, cell_spec["cell"], html_rel_path, spec_rel_path
+            )
+
+
+def assert_element_comply_with_spec(
+    element: Union[Document, _Cell], spec: dict, html_rel_path: str, spec_rel_path: str
+):
+    children = list(get_document_children(element))
+    assert len(children) == len(spec)
+    for child, child_spec in zip(children, spec):
+        if isinstance(child, Paragraph):
+            assert_paragraph_comply_with_spec(
+                child, child_spec, html_rel_path, spec_rel_path
+            )
+        if isinstance(child, Table):
+            assert_table_comply_with_spec(
+                child, child_spec, html_rel_path, spec_rel_path
+            )
+
+
 @pytest.mark.parametrize("html_path,spec_path", generate_testdata())
@@ -44,33 +127,2 @@ def test_html2docx(html_path, spec_path):
     assert doc.core_properties.title == title
-    assert len(doc.paragraphs) == len(spec)
-    for p, p_spec in zip(doc.paragraphs, spec):
-        assert p.text == p_spec["text"]
-        assert p.style.name == p_spec.get("style", "Normal")
-        if p_spec.get("alignment") is not None:
-            assert p.alignment == p_spec["alignment"]
-        else:
-            assert p.alignment is None
-        if p_spec.get("left_indent"):
-            assert p.paragraph_format.left_indent == Pt(p_spec["left_indent"])
-        else:
-            assert p.paragraph_format.left_indent is None
-
-        runs_spec = p_spec["runs"]
-        assert len(p.runs) == len(runs_spec)
-        for run, run_spec in zip(p.runs, runs_spec):
-            assert run.text == run_spec.pop("text")
-            shapes_spec = run_spec.pop("shapes", None)
-            unknown = set(run_spec).difference(FONT_ATTRS)
-            assert not unknown, "Unknown attributes in {}: {}".format(
-                spec_rel_path, ", ".join(unknown)
-            )
-            for attr in FONT_ATTRS:
-                msg = f"Wrong {attr} for text '{run.text}' in {html_rel_path}"
-                assert getattr(run.font, attr) == run_spec.get(attr), msg
-            if shapes_spec:
-                shapes = run.part.inline_shapes
-                assert len(shapes) == len(shapes_spec)
-                for shape, shape_spec in zip(shapes, shapes_spec):
-                    assert shape.type == shape_spec["type"]
-                    assert shape.width == shape_spec["width"]
-                    assert shape.height == shape_spec["height"]
+    assert_element_comply_with_spec(doc, spec, html_rel_path, spec_rel_path)

Alert delta unavailable

Currently unable to show alert delta for PyPI packages.

Improved metrics

Total package byte prevSize

93480

4.37%

Number of package files

110

1.85%

Lines of code

1595

7.7%