tools: improve v check-md by checking for broken TOC headline links (#10417)

cmd/tools/vcheck-md.v

@@ -9,6 +9,7 @@ import rand
 import term
 import vhelp
 import v.pref
+import regex
 
 const (
 	too_long_line_length = 100
@@ -162,6 +163,7 @@ fn (mut f MDFile) progress(message string) {
 
 fn (mut f MDFile) check() CheckResult {
 	mut res := CheckResult{}
+	mut anchor_data := AnchorData{}
 	for j, line in f.lines {
 		// f.progress('line: $j')
 		if line.len > too_long_line_length {
@@ -187,8 +189,14 @@ fn (mut f MDFile) check() CheckResult {
 				res.errors++
 			}
 		}
+		if f.state == .markdown {
+			anchor_data.add_links(j, line)
+			anchor_data.add_link_targets(j, line)
+		}
+
 		f.parse_line(j, line)
 	}
+	anchor_data.check_link_target_match(f.path, mut res)
 	res += f.check_examples()
 	return res
 }
@@ -234,6 +242,121 @@ fn (mut f MDFile) parse_line(lnumber int, line string) {
 	}
 }
 
+struct Headline {
+	line  int
+	lable string
+	level int
+}
+
+struct Anchor {
+	line int
+}
+
+type AnchorTarget = Anchor | Headline
+
+struct AnchorLink {
+	line  int
+	lable string
+}
+
+struct AnchorData {
+mut:
+	links   map[string][]AnchorLink
+	anchors map[string][]AnchorTarget
+}
+
+fn (mut ad AnchorData) add_links(line_number int, line string) {
+	query := r'\[(?P<lable>[^\]]+)\]\(\s*#(?P<link>[a-z\-]+)\)'
+	mut re := regex.regex_opt(query) or { panic(err) }
+	res := re.find_all_str(line)
+
+	for elem in res {
+		re.match_string(elem)
+		link := re.get_group_by_name(elem, 'link')
+		ad.links[link] << AnchorLink{
+			line: line_number
+			lable: re.get_group_by_name(elem, 'lable')
+		}
+	}
+}
+
+fn (mut ad AnchorData) add_link_targets(line_number int, line string) {
+	if line.trim_space().starts_with('#') {
+		if headline_start_pos := line.index(' ') {
+			headline := line.substr(headline_start_pos + 1, line.len)
+			link := create_ref_link(headline)
+			ad.anchors[link] << Headline{
+				line: line_number
+				lable: headline
+				level: headline_start_pos
+			}
+		}
+	} else {
+		query := r'<a\s*id=["\'](?P<link>[a-z\-]+)["\']\s*/>'
+		mut re := regex.regex_opt(query) or { panic(err) }
+		res := re.find_all_str(line)
+
+		for elem in res {
+			re.match_string(elem)
+			link := re.get_group_by_name(elem, 'link')
+			ad.anchors[link] << Anchor{
+				line: line_number
+			}
+		}
+	}
+}
+
+fn (mut ad AnchorData) check_link_target_match(fpath string, mut res CheckResult) {
+	mut checked_headlines := []string{}
+	mut found_error_warning := false
+	for link, linkdata in ad.links {
+		if link in ad.anchors {
+			checked_headlines << link
+			if ad.anchors[link].len > 1 {
+				found_error_warning = true
+				res.errors++
+				for anchordata in ad.anchors[link] {
+					eprintln(eline(fpath, anchordata.line, 0, 'multiple link targets of existing link (#$link)'))
+				}
+			}
+		} else {
+			found_error_warning = true
+			res.errors++
+			for brokenlink in linkdata {
+				eprintln(eline(fpath, brokenlink.line, 0, 'no link target found for existing link [$brokenlink.lable](#$link)'))
+			}
+		}
+	}
+	for link, anchor_lists in ad.anchors {
+		if !(link in checked_headlines) {
+			if anchor_lists.len > 1 {
+				for anchor in anchor_lists {
+					line := match anchor {
+						Headline {
+							anchor.line
+						}
+						Anchor {
+							anchor.line
+						}
+					}
+					wprintln(wline(fpath, line, 0, 'multiple link target for non existing link (#$link)'))
+					found_error_warning = true
+					res.warnings++
+				}
+			}
+		}
+	}
+	if found_error_warning {
+		eprintln('') // fix suppressed last error output
+	}
+}
+
+fn create_ref_link(s string) string {
+	query_remove := r'[^a-z \-]'
+	mut re := regex.regex_opt(query_remove) or { panic(err) }
+	return re.replace_simple(s.to_lower(), '').replace(' ', '-')
+}
+
 fn (mut f MDFile) debug() {
 	for e in f.examples {
 		eprintln('f.path: $f.path | example: $e')

doc/docs.md

@@ -83,7 +83,7 @@ For more details and troubleshooting, please visit the [vab GitHub repository](h
 * [Structs](#structs)
     * [Embedded structs](#embedded-structs)
     * [Default field values](#default-field-values)
-    * [Short struct literal syntax](#short-struct-initialization-syntax)
+    * [Short struct literal syntax](#short-struct-literal-syntax)
     * [Access modifiers](#access-modifiers)
     * [Methods](#methods)
 * [Unions](#unions)
@@ -2270,7 +2270,7 @@ You can also install modules already created by someone else with [VPM](https://
 ```powershell
 v install [module]
 ```
-###### Example:
+**Example:**
 ```powershell
 v install ui
 ```
@@ -2280,7 +2280,7 @@ Removing a module with v:
 ```powershell
 v remove [module]
 ```
-###### Example:
+**Example:**
 ```powershell
 v remove ui
 ```
@@ -2290,7 +2290,7 @@ Updating an installed module from [VPM](https://vpm.vlang.io/):
 ```powershell
 v update [module]
 ```
-###### Example:
+**Example:**
 ```powershell
 v update ui
 ```
@@ -2305,7 +2305,7 @@ To see all the modules you have installed, you can use:
 ```powershell
 v list
 ```
-###### Example
+**Example:**
 ```powershell
 > v list
 Installed modules:
@@ -2318,7 +2318,7 @@ outdated          Show installed modules that need updates.
 ```powershell
 v outdated
 ```
-###### Example
+**Example:**
 ```powershell
 > v outdated
 Modules are up to date.
@@ -4024,7 +4024,7 @@ created by the JS Backend (flag: `-b js`).
 
 `$` is used as a prefix for compile-time operations.
 
-#### $if
+#### `$if` condition
 ```v
 // Support for multiple conditions in one branch
 $if ios || android {
@@ -4076,7 +4076,7 @@ Full list of builtin options:
 | `gnu`, `hpux`, `haiku`, `qnx` | `cplusplus`       | `big_endian`          |
 | `solaris` | | | |
 
-#### $embed_file
+#### `$embed_file`
 
 ```v ignore
 import os
@@ -4099,7 +4099,7 @@ executable, increasing your binary size, but making it more self contained
 and thus easier to distribute. In this case, `f.data()` will cause *no IO*,
 and it will always return the same data.
 
-#### $tmpl for embedding and parsing V template files
+#### `$tmpl` for embedding and parsing V template files
 
 V has a simple template language for text and html templates, and they can easily
 be embedded via `$tmpl('path/to/template.txt')`:
@@ -4149,7 +4149,7 @@ numbers: [1, 2, 3]
 
 
 
-#### $env
+#### `$env`
 
 ```v
 module main

doc/upcoming.md

@@ -74,37 +74,37 @@ different capabilities:
 | structured data types     |     +     |   +   |     +    |          |
 
 ### Strengths
-#### default
+**default**
 - very fast
 - unlimited access from different coroutines
 - easy to handle
 
-#### `mut`
+**`mut`**
 - very fast
 - easy to handle
 
-#### `shared`
+**`shared`**
 - concurrent access from different coroutines
 - data type may be complex structure
 - sophisticated access possible (several statements within one `lock`
   block)
 
-#### `atomic`
+**`atomic`**
 - concurrent access from different coroutines
 - reasonably fast
 
 ### Weaknesses
-#### default
+**default**
 - read only
 
-#### `mut`
+**`mut`**
 - access only from one coroutine at a time
 
-#### `shared`
+**`shared`**
 - lock/unlock are slow
 - moderately difficult to handle (needs `lock` block)
 
-#### `atomic`
+**`atomic`**
 - limited to single (max. 64 bit) integers (and pointers)
 - only a small set of predefined operations possible
 - very difficult to handle correctly
@@ -191,3 +191,5 @@ are sometimes surprising. Each statement should be seen as a single
 transaction that is unrelated to the previous or following
 statement. Therefore - but also for performance reasons - it's often
 better to group consecutive coherent statements in an explicit `lock` block.
+
+### Channels

doc/vscode.md

@@ -23,7 +23,7 @@ provides V language support for Visual Studio Code.
 [install V compiler](https://github.com/vlang/v/blob/master/doc/docs.md#install-from-source)
 on your operating system.
 
-### Setup
+### Setup Extention
 
 Install [V VS Code Extention](https://marketplace.visualstudio.com/items?itemName=vlanguage.vscode-vlang).
 
@@ -45,7 +45,7 @@ for Visual Studio Code provides visual conditional debugging.
 [DWARF](https://en.wikipedia.org/wiki/DWARF) information to show and 
 edit the variable.
 
-### Setup
+### Setup Debugging
 
 1. Install the [C/C++ Extention](https://marketplace.visualstudio.com/items?itemName=ms-vscode.cpptools)
 2. Open `RUN AND DEBUG` panel (Debug Icon in left panel).

vlib/v/TEMPLATES.md

@@ -1,9 +1,11 @@
-This package is to generate data-driven HTML output.
+V allows for easily using text templates, expanded at compile time to
+V functions, that efficiently produce text output. This is especially
+usefull for templated HTML views, but the mechanism is general enough
+to be used for other kinds of text output also.
 
-# Directives
+# Template directives
-Each directive begins with an `@` sign.
+Each template directive begins with an `@` sign.
-Some directives begin contains a `{}` block, others only have `''` (string) parameters.
+Some directives contain a `{}` block, others only have `''` (string) parameters.
-More on the directives itself.
 
 Newlines on the beginning and end are ignored in `{}` blocks,
 otherwise this (see [if](#if) for this syntax):
@@ -12,17 +14,17 @@ otherwise this (see [if](#if) for this syntax):
     <span>This is shown if bool_val is true</span>
 }
 ```
-would result in:
+... would output:
 ```html
 
     <span>This is shown if bool_val is true</span>
 
 ```
-which could result in unreadable output.
+... which is less readable.
 
 ## if
-The if directive consists of three parts, the `@if` tag, the condition (same syntax like in V)
+The if directive, consists of three parts, the `@if` tag, the condition (same syntax like in V)
-and the `{}` block where you can write html which will be rendered if the condition is true:
+and the `{}` block, where you can write html, which will be rendered if the condition is true:
 ```
 @if <condition> {}
 ```
@@ -42,19 +44,20 @@ The first example would result in:
 ```html
     <span>This is shown if bool_val is true</span>
 ```
-while the one-liner results in:
+... while the one-liner results in:
 ```html
 <span>This is shown if bool_val is true</span>
 ```
 
 ## for
-The for directive consists of three parts, the `@for` tag, the condition (same syntax like in V)
+The for directive consists of three parts, the `@for` tag,
-and the `{}` block where you can write html which will be rendered for each loop:
+the condition (same syntax like in V) and the `{}` block,
+where you can write text, rendered for each iteration of the loop:
 ```
 @for <condition> {}
 ```
 
-### Example
+### Example for @for
 ```html
 @for i, val in my_vals {
     <span>$i - $val</span>
@@ -72,7 +75,7 @@ The first example would result in:
     <span>2 - "Third"</span>
     ...
 ```
-while the one-liner results in:
+... while the one-liner results in:
 ```html
 <span>0 - "First"</span>
 <span>1 - "Second"</span>
@@ -92,8 +95,7 @@ The include directive is for including other html files (which will be processed
 and consists of two parts, the `@include` tag and a following `'<path>'` string.
 The path parameter is relative to the `/templates` directory in the corresponding project.
 
-### Example
+### Example for the folder structure of a project using templates:
-Files
 ```
 Project root
 /templates
@@ -117,11 +119,11 @@ where you can insert your src
 @js '<url>'
 ```
 
-### Example
+### Example for the @js directive:
 ```html
 @js 'myscripts.js'
 ```
 
 # Variables
-All variables which are declared before can be used through the `@{my_var}` syntax.
+All variables, which are declared before the $tmpl can be used through the `@{my_var}` syntax.
 It's also possible to use properties of structs here like `@{my_struct.prop}`.