From 667e7be221a21e488667a1af7203c1c0e81efc73 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Guillaume=20H=C3=A9rail?= <guillaume@herail.net>
Date: Wed, 25 Jan 2023 10:52:00 +0100
Subject: [PATCH 1/2] fix: Title not being extracted when not on the first line

While a page with a macro is processed, having a macro leaves an unclean buffer
for further processing steps, including title extraction.  The problem seems to
come from `ExtractMeta`: as it runs through the metadata, it hits the first
line of the macro but since it doesn't look like a complete Metadata (e.g.
matching either `\[\]:\s*#\s*\(([^:]+):\s*(.*)\)` or
`<!--\s*([^:]+):\s*(.*)\s*-->` in
https://github.com/kovetskiy/mark/blob/master/pkg/mark/meta.go#L37:L38, it will
break the loop in
https://github.com/kovetskiy/mark/blob/master/pkg/mark/meta.go#L61 and return
the final document as:
```
  Template: ac:children
  Style: h2
  Excerpt: none
  Page:
  TestSpace:Test
  Reverse: false
  All: true -->

:children:
```

This then goes into `ExtractDocumentLeadingH1` which doesn't find a match for
the regex `^#[^#]\s*(.*)\s*\n`, returning an empty title since the title is not
on the first line. This commit, while it doesn't fix the unclean document,
fixes the regex to properly find the title.

Closes #214
---
 pkg/mark/markdown.go        | 2 +-
 pkg/mark/testdata/header.md | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/pkg/mark/markdown.go b/pkg/mark/markdown.go
index 98576c0..ddea59f 100644
--- a/pkg/mark/markdown.go
+++ b/pkg/mark/markdown.go
@@ -345,7 +345,7 @@ func DropDocumentLeadingH1(
 
 // ExtractDocumentLeadingH1 will extract leading H1 heading
 func ExtractDocumentLeadingH1(markdown []byte) string {
-	h1 := regexp.MustCompile(`^#[^#]\s*(.*)\s*\n`)
+	h1 := regexp.MustCompile(`#[^#]\s*(.*)\s*\n`)
 	groups := h1.FindSubmatch(markdown)
 	if groups == nil {
 		return ""
diff --git a/pkg/mark/testdata/header.md b/pkg/mark/testdata/header.md
index 9c1d2f0..81a9738 100644
--- a/pkg/mark/testdata/header.md
+++ b/pkg/mark/testdata/header.md
@@ -1,3 +1,4 @@
+
 # a
 ## b
 ### c

From 1b3c7b4127c2125bfa0a780d4e65703f29ab0ee2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Guillaume=20H=C3=A9rail?= <guillaume@herail.net>
Date: Wed, 25 Jan 2023 13:08:08 +0100
Subject: [PATCH 2/2] fix: Properly handle macro when extracting Metadata
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When a macro is set in the header, only the first line will be read and then
discarded. This makes sure we keep the macro in and stop processing metadata
when we hit a macro.

Co-authored-by: Manuel Rüger <manuel@rueg.eu>
---
 README.md        |  3 +++
 pkg/mark/meta.go | 11 +++++++++--
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 1e70b76..f288534 100644
--- a/README.md
+++ b/README.md
@@ -120,6 +120,9 @@ be replaced with specified template:
      <yaml-data> -->
 ```
 
+**NOTE**: Make sure to define your macros after your metadata (Title/Space), 
+mark will stop processing metadata if it hits a Macro.
+
 Capture groups can be defined in the macro's <regexp> which can be later
 referenced in the `<yaml-data>` using `${<number>}` syntax, where `<number>` is
 number of a capture group in regexp (`${0}` is used for entire regexp match),
diff --git a/pkg/mark/meta.go b/pkg/mark/meta.go
index 2f1a301..416182b 100644
--- a/pkg/mark/meta.go
+++ b/pkg/mark/meta.go
@@ -34,8 +34,9 @@ type Meta struct {
 }
 
 var (
-	reHeaderPatternV1 = regexp.MustCompile(`\[\]:\s*#\s*\(([^:]+):\s*(.*)\)`)
-	reHeaderPatternV2 = regexp.MustCompile(`<!--\s*([^:]+):\s*(.*)\s*-->`)
+	reHeaderPatternV1    = regexp.MustCompile(`\[\]:\s*#\s*\(([^:]+):\s*(.*)\)`)
+	reHeaderPatternV2    = regexp.MustCompile(`<!--\s*([^:]+):\s*(.*)\s*-->`)
+	reHeaderPatternMacro = regexp.MustCompile(`<!-- Macro: .*`)
 )
 
 func ExtractMeta(data []byte) (*Meta, []byte, error) {
@@ -58,6 +59,12 @@ func ExtractMeta(data []byte) (*Meta, []byte, error) {
 		if matches == nil {
 			matches = reHeaderPatternV1.FindStringSubmatch(line)
 			if matches == nil {
+				matches = reHeaderPatternMacro.FindStringSubmatch(line)
+				// If we have a match, then we started reading a macro.
+				// We want to keep it in the document for it to be read by ExtractMacros
+				if matches != nil {
+					offset -= len(line) + 1
+				}
 				break
 			}