From 49b19f06a650607c176b6671d39c7307f2d1fccd Mon Sep 17 00:00:00 2001
From: cyy-2024 <1491909552@qq.com>
Date: Thu, 24 Oct 2024 09:29:37 +0800
Subject: [PATCH] [fix][html_parser] Improved inline image rendering for proper
 text-image alignment

---
 .idea/.gitignore                              |  8 ++++++
 .idea/html2docx.iml                           | 12 +++++++++
 .../inspectionProfiles/profiles_settings.xml  |  6 +++++
 .idea/misc.xml                                |  7 ++++++
 .idea/modules.xml                             |  8 ++++++
 .idea/vcs.xml                                 |  6 +++++
 htmldocx/h2d.py                               | 25 ++++++++++++++++---
 mytest.py                                     | 12 +++++++++
 8 files changed, 81 insertions(+), 3 deletions(-)
 create mode 100644 .idea/.gitignore
 create mode 100644 .idea/html2docx.iml
 create mode 100644 .idea/inspectionProfiles/profiles_settings.xml
 create mode 100644 .idea/misc.xml
 create mode 100644 .idea/modules.xml
 create mode 100644 .idea/vcs.xml
 create mode 100644 mytest.py

diff --git a/.idea/.gitignore b/.idea/.gitignore
new file mode 100644
index 0000000..13566b8
--- /dev/null
+++ b/.idea/.gitignore
@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
diff --git a/.idea/html2docx.iml b/.idea/html2docx.iml
new file mode 100644
index 0000000..8b8c395
--- /dev/null
+++ b/.idea/html2docx.iml
@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>
\ No newline at end of file
diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml
new file mode 100644
index 0000000..105ce2d
--- /dev/null
+++ b/.idea/inspectionProfiles/profiles_settings.xml
@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
new file mode 100644
index 0000000..3820285
--- /dev/null
+++ b/.idea/misc.xml
@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.12 (html2docx)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12 (html2docx)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100644
index 0000000..6f399d9
--- /dev/null
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/html2docx.iml" filepath="$PROJECT_DIR$/.idea/html2docx.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 0000000..35eb1dd
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file
diff --git a/htmldocx/h2d.py b/htmldocx/h2d.py
index 6a0e113..318396d 100644
--- a/htmldocx/h2d.py
+++ b/htmldocx/h2d.py
@@ -601,11 +601,30 @@ def run_process(self, html):
 
     def add_html_to_document(self, html, document):
         if not isinstance(html, str):
-            raise ValueError('First argument needs to be a %s' % str)
+            raise ValueError('First argument needs to be a string')
         elif not isinstance(document, docx.document.Document) and not isinstance(document, docx.table._Cell):
-            raise ValueError('Second argument needs to be a %s' % docx.document.Document)
+            raise ValueError('Second argument needs to be a Document or a Cell object')
+
         self.set_initial_attrs(document)
-        self.run_process(html)
+        soup = BeautifulSoup(html, 'html.parser')
+        self.paragraph = document.add_paragraph()
+        for element in soup.descendants:
+            if isinstance(element, str):
+                self.run = self.paragraph.add_run(element.strip())
+            elif element.name == 'img':
+
+                img_path = element.get('src')
+                width = element.get('width', 100)
+                height = element.get('height', 50)
+                self.run = self.paragraph.add_run()
+                self.run.add_picture(img_path, width=Inches(float(width) / 100), height=Inches(float(height) / 100))
+            else:
+                continue
+
+
+        paragraph_format = self.paragraph.paragraph_format
+        paragraph_format.line_spacing = 1.0
+        paragraph_format.keep_with_next = True
 
     def add_html_to_cell(self, html, cell):
         if not isinstance(cell, docx.table._Cell):
diff --git a/mytest.py b/mytest.py
new file mode 100644
index 0000000..5434f48
--- /dev/null
+++ b/mytest.py
@@ -0,0 +1,12 @@
+from docx import Document
+from htmldocx import HtmlToDocx
+
+document = Document()
+new_parser = HtmlToDocx()
+
+html = '''
+<p>there are some words：<img src="testimg.png"D:/kaiyuan/html2docx/testimg.png width="100" height="50" alt="测试图片"/>，there are some words in the same line。</p>
+'''
+
+new_parser.add_html_to_document(html, document)
+document.save('test_output.docx')