Commit 9328ebdb authored by ankraft's avatar ankraft
Browse files

Added support for merging consecutive code paragraphs into a single code block

parent e0ababce

README.md

+3 −2
Original line number Original line Diff line number Diff line
@@ -12,8 +12,8 @@ python3 -m pip install -r requirements.txt 




## Usage

## Usage

- Create a directory with the Word document in it. The Word document **must** be in *docx* format. This can be achieved by opening the document with *Word* and save it in *docx* format to another file.

- Create a directory with the Word document in it. The Word document **must** be in *docx* format. This can be achieved by opening the document with *Word* and save it in *docx* format to another file.

- Create a configuration file with the same base name as the Word document + *.ini* extension. This file may contain different configurations as the standard *config.ini* file provided. 

- Optional: Create a configuration file *config.ini* in that directory. This file may contain different configurations as the configuratioon file in the project's root directory. This confiuration file will apply to all files in that directory

	- Alternatively, a file named *config.ini* will apply to all files in that directory.

	- Alternatively, a configuration wile with the same base name as the Word document. This configuration file will only apply to the Word document with the same base name.

	- It is only necessary to add the settings that are different from the *config.ini* file in the project's root directory. That file will always act as a fallback.

	- It is only necessary to add the settings that are different from the *config.ini* file in the project's root directory. That file will always act as a fallback.

- Run the converter as follows:

- Run the converter as follows:

```

```
@@ -63,5 +63,6 @@ Lists in table cells are also not possible. One may use html lists for this, but 




## Changes

## Changes





- **2024-01-09** - Added support for merging consecutive code paragraphs into a single code block.

- **2023-08-18** - Improved handling of sometimes broken inline formatting in table cells. Adding more default heading formats.

- **2023-08-18** - Improved handling of sometimes broken inline formatting in table cells. Adding more default heading formats.

- **2023-07-27** - Added converting bold and italic text in paragraphs, headers and tables.
 
- **2023-07-27** - Added converting bold and italic text in paragraphs, headers and tables.
 
 No newline at end of file

config.ini

+9 −2
Original line number Original line Diff line number Diff line
@@ -7,8 +7,12 @@ 








[general]

[general]

# Replace non-breaking spaces in the word document with an HTML space entity.

replaceNbsp =  

replaceNbsp =  





# Replace the less than character in the word document with an HTML entity.

replaceLt = <



; Rename EMF/WMF image references to a different file extension.

; Rename EMF/WMF image references to a different file extension.

; Allowed values: png, svg.

; Allowed values: png, svg.

; If not preseent, no renaming will happen.

; If not preseent, no renaming will happen.
@@ -18,12 +22,14 @@ renameEMFExtension = svg 
; Default: false

; Default: false

skipUnreferencedMediaFiles = false

skipUnreferencedMediaFiles = false





replaceLt = <

# Combine code paragraphs into a single markdown code paragraph.

combineCodeParagraphs = true





; Add image captions to the markdown's alternate text.

; Add image captions to the markdown's alternate text.

; Note, that the image caption has follow the image in the document.

; Note, that the image caption has follow the image in the document.

imageCaptions2AltText = true

imageCaptions2AltText = true







[toc]

[toc]

addSectionNumbers = false

addSectionNumbers = false

excludeFromNumbering =

excludeFromNumbering =
@@ -35,7 +41,7 @@ addTocMacro = false 




[paragraphs]

[paragraphs]

normal = normal

normal = normal

h1 = heading 1

h1 = heading 1, tt

h2 = heading 2

h2 = heading 2

h3 = heading 3

h3 = heading 3

h4 = heading 4

h4 = heading 4
@@ -48,6 +54,7 @@ a1 = heading 1 
a2 = heading 2

a2 = heading 2

a3 = heading 3

a3 = heading 3

note = no

note = no

code = pl

example = ex, ew

example = ex, ew

ul1 = b1, b1+, list paragraph

ul1 = b1, b1+, list paragraph

ul2 = b2, b2+

ul2 = b2, b2+

spec2md.py

+32 −0
Original line number Original line Diff line number Diff line
@@ -27,6 +27,7 @@ import configparser, zipfile 
from lxml import etree as ET

from lxml import etree as ET





class Style(IntEnum):

class Style(IntEnum):

	code = auto()

	example = auto()

	example = auto()

	image = auto()

	image = auto()

	imagecaption = auto()

	imagecaption = auto()
@@ -145,6 +146,7 @@ class DocumentConfiguration(object): 
		self.renameEMFExtension = config.get('general', 'renameEMFExtension', fallback = None)

		self.renameEMFExtension = config.get('general', 'renameEMFExtension', fallback = None)

		self.skipUnreferencedMediaFiles = config.getboolean('general', 'skipUnreferencedMediaFiles', fallback = False)

		self.skipUnreferencedMediaFiles = config.getboolean('general', 'skipUnreferencedMediaFiles', fallback = False)

		self.imageCaptions2AltText = config.getboolean('general', 'imageCaptions2AltText', fallback = True)

		self.imageCaptions2AltText = config.getboolean('general', 'imageCaptions2AltText', fallback = True)

		self.combineCodeParagraphs = config.getboolean('general', 'combineCodeParagraphs', fallback = True)





		#	Paragraphs

		#	Paragraphs

		self.paragraphs = { c : config.getlist('paragraphs', c)	# type: ignore [attr-defined]

		self.paragraphs = { c : config.getlist('paragraphs', c)	# type: ignore [attr-defined]
@@ -170,6 +172,7 @@ class DocumentConfiguration(object): 
		self.ul4 = self.paragraphs['ul4']

		self.ul4 = self.paragraphs['ul4']

		self.ul5 = self.paragraphs['ul5']

		self.ul5 = self.paragraphs['ul5']

		#self.continuedlist = self.paragraphs['continuedlist']

		#self.continuedlist = self.paragraphs['continuedlist']

		self.code = self.paragraphs['code']

		self.note = self.paragraphs['note']

		self.note = self.paragraphs['note']

		self.example = self.paragraphs['example']

		self.example = self.paragraphs['example']

		self.tablecaption = self.paragraphs['tablecaption']

		self.tablecaption = self.paragraphs['tablecaption']
@@ -653,6 +656,12 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion: 
							lines.append('')

							lines.append('')

							lines.append(text)

							lines.append(text)





						#	Code

						elif style in docConfig.code:

							checkSameStyle(Style.code, lambda:lines.append(''))

							for _t in text.split(_linebreak):

								lines.append(f'```{_t if _t else " "}```  ') # at least an empty space. And 2 spaces at the end for newline



						#	Example

						#	Example

						elif style in docConfig.example:

						elif style in docConfig.example:

							checkSameStyle(Style.example, lambda:lines.append(''))

							checkSameStyle(Style.example, lambda:lines.append(''))
@@ -745,6 +754,29 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion: 
				lines[i] = line

				lines[i] = line









			#

			#	Combine mutiple consecutive "code" lines

			#



			if docConfig.combineCodeParagraphs:

				codeblock:list[str] = []

				_lines:list[str] = []

				for i in range(len(lines)):

					line = lines[i]

					if line.startswith('```') and line.endswith('```  '):

						# Store code block

						codeblock.append(line[3:-5])

					elif codeblock:

						# Add whole code block to lines

						_lines.append('```')

						_lines.extend(codeblock)

						_lines.append('```')

						codeblock = []

					else:

						# Add line

						_lines.append(line)

				lines = _lines



			#

			#

			#	Insert auto-generated table of contents

			#	Insert auto-generated table of contents

			#

			#