Merge pull request #161 from theohbrothers/enhancement/config-add-ability-for-keepspaces-option-to-strip-extra-newline-between-ordered-list-items

leojonathanoh · web-flow · commit 07c917596e64 · 2023-05-03T06:22:11.000Z
Enhancement (config): Add ability for `$keepspaces` option to strip extra newline between ordered list items
diff --git a/ConvertOneNote2MarkDown-v2.Tests.ps1 b/ConvertOneNote2MarkDown-v2.Tests.ps1
@@ -1190,6 +1190,7 @@ Describe 'New-SectionGroupConversionConfig' -Tag 'Unit' {
 
             $fakeMarkdownContent = @"
 hello world$( [char]0x00A0 )
+
 - foo
 
   - foo1
@@ -1198,9 +1199,29 @@ hello world$( [char]0x00A0 )
 
   - bar1
 
+- baz
+
+  - baz1
+
 >
 >
 > some other text
+
+1. foo
+
+    1. foo1
+
+2. bar
+
+    1. bar1
+
+3. baz
+
+    1. baz1
+
+some new paragraph
+some more
+
 "@ -replace "`r", '' # On some Windows Powershell 5 versions, a here-string will contain `\r`, so let's ensure that doesn't happen.
 
             foreach ($pageCfg in $result) {
@@ -1212,19 +1233,33 @@ hello world$( [char]0x00A0 )
                     }
                 }
 
-                # Should remove newlines between bullets, and remove non-breaking spaces. Ignore first 8 lines for page header
+                # Should remove extra newline between unordered and ordered lists, remove non-breaking spaces, and '>' from ordered lists. Ignore first 8 lines for page header
                 $split = $mutated -split "`n"
                 $expectedBody = $split[8..($split.Count - 1)] -join "`n"
                 $expectedBody | Should -Be $( @"
 hello world
+
 - foo
   - foo1
 - bar
   - bar1
+- baz
+  - baz1
 
 
 
 some other text
+
+1. foo
+    1. foo1
+2. bar
+    1. bar1
+3. baz
+    1. baz1
+
+some new paragraph
+some more
+
 "@ -replace "`r", '') # On some Windows Powershell 5 versions, a here-string will contain `\r`, so let's ensure that doesn't happen.
             }
 
@@ -1244,23 +1279,10 @@ some other text
                     }
                 }
 
-                # Should keep newlines between bullets, and keep non-breaking spaces. Ignore first 8 lines for page header
+                # Should keep extra newline between ordered and unordered list items, keep non-breaking spaces, and `>` from ordered lists. Ignore first 8 lines for page header
                 $split = $mutated -split "`n"
                 $expectedBody = $split[8..($split.Count - 1)] -join "`n"
-                $expectedBody | Should -Be $( @"
-hello world$( [char]0x00A0 )
-- foo
-
-  - foo1
-
-- bar
-
-  - bar1
-
->
->
-> some other text
-"@ -replace "`r", '') # On some Windows Powershell 5 versions, a here-string will contain `\r`, so let's ensure that doesn't happen.
+                $expectedBody | Should -Be $fakeMarkdownContent # On some Windows Powershell 5 versions, a here-string will contain `\r`, so let's ensure that doesn't happen.
             }
 
         }
diff --git a/ConvertOneNote2MarkDown-v2.ps1 b/ConvertOneNote2MarkDown-v2.ps1
@@ -152,9 +152,9 @@ Whether to include page timestamp and separator at top of document
         }
         keepspaces = @{
             description = @'
-Whether to clear double spaces between bullets, non-breaking spaces from blank lines, and '>` after bullet lists
-1: Clear double spaces in bullets - Default
-2: Keep double spaces
+Whether to clear extra newlines between unordered (bullet) and ordered (numbered) list items, non-breaking spaces from blank lines, and `>` after unordered lists
+1: Clear - Default
+2: Don't clear
 '@
             default = 1
             value = 1
@@ -928,18 +928,24 @@ Function New-SectionGroupConversionConfig {
                             }
                             if ($config['keepspaces']['value'] -eq 1 ) {
                                 @{
-                                    description = 'Clear double spaces from bullets and non-breaking spaces spaces from blank lines'
+                                    description = 'Clear extra newlines between unordered (bullet) and ordered (numbered) list items, non-breaking spaces from blank lines, and `>` after unordered lists'
                                     replacements = @(
+                                        # Remove non-breaking spaces
                                         @{
                                             searchRegex = [regex]::Escape([char]0x00A0)
                                             replacement = ''
                                         }
-                                        # Remove a newline between each occurrence of '- some list item'
+                                        # Remove an extra newline between each occurrence of '- some unordered list item'
                                         @{
-                                            searchRegex = '\r*\n\r*\n(\s*)- '
-                                            replacement = "`n`$1- "
+                                            searchRegex = '(\s*)- ([^\r\n]*)\r*\n\r*\n(?=\s*-)'
+                                            replacement = "`$1- `$2`n"
                                         }
-                                        # Remove all '>' occurrences immediately following bullet lists
+                                        # Remove an extra newline between each occurrence of '1. some ordered list item'
+                                        @{
+                                            searchRegex = '(\s*)(\d+\.) ([^\r\n]*)\r*\n\r*\n(?=\s*\d+\.)'
+                                            replacement = "`$1`$2 `$3`n"
+                                        }
+                                        # Remove all '>' occurrences immediately following unordered lists
                                         @{
                                             searchRegex = '\n>[ ]*'
                                             replacement = "`n"
diff --git a/README.md b/README.md
@@ -29,7 +29,7 @@ The powershell script `ConvertOneNote2MarkDown-v2.ps1` will utilize the OneNote
   * `markdown_phpextra` (PHP Markdown Extra)
   * `markdown_strict` (original unextended Markdown)
   * Improved headers, with title now as a `#` heading, standardized `DateTime` format for created and modified dates, and horizontal line to separate from rest of document
-* Choose whether to remove double spaces between bullet points, non-breaking spaces from blank lines, and `>` after bullet lists, which are created when converting with Pandoc
+* Choose whether to clear extra newlines between unordered (bullet) and ordered (numbered) list items, non-breaking spaces from blank lines, and `>` after unordered lists, which are created when converting with Pandoc
 * Choose whether to remove `\` escape symbol that are created when converting with Pandoc
 * Choose whether to use Line Feed (`LF`) or Carriage Return + Line Feed (`CRLF`) for new lines
 * Choose whether to include a `.pdf` export alongside the `.md` file. `.md` does not preserve `InkDrawing` (i.e. overlayed drawings, highlights, pen marks) absolute positions within a page, but a `.pdf` export is a complete page snapshot that preserves `InkDrawing` absolute positions within a page.
diff --git a/config.example.ps1 b/config.example.ps1
@@ -68,9 +68,9 @@ $conversion = 'markdown-simple_tables-multiline_tables-grid_tables+pipe_tables'
 # 2: Don't include
 $headerTimestampEnabled = 1
 
-# Whether to clear double spaces between bullets, non-breaking spaces from blank lines, and '>` after bullet lists
-# 1: Clear double spaces in bullets - Default
-# 2: Keep double spaces
+# Whether to clear extra newlines between unordered (bullet) and ordered (numbered) list items, non-breaking spaces from blank lines, and `>` after unordered lists
+# 1: Clear - Default
+# 2: Don't clear
 $keepspaces = 1
 
 # Whether to clear escape symbols from md files. See: https://pandoc.org/MANUAL.html#backslash-escapes
