Fix headline tags, table pretty printing and multiline links

- we can't just look at the len of the string (~ #bytes) - that breaks down for
  tables containing characters consisting of multiple bytes. This handles
  more (still not all) cases and is good enough for now
- add _ to allowed tag chars - also require space between headline and tags
- links (link itself, not the description) spanning multiple lines are not
  supported - otherwise we would have to take care of splitting link and adding
  indentation for org pretty printing - and that sounds like such an edge case
  that it seems cleaner to forbid them

org/headline.go

@@ -17,7 +17,7 @@ type Headline struct {
 }
 
 var headlineRegexp = regexp.MustCompile(`^([*]+)\s+(.*)`)
-var tagRegexp = regexp.MustCompile(`(.*?)\s*(:[A-Za-z0-9@#%:]+:\s*$)`)
+var tagRegexp = regexp.MustCompile(`(.*?)\s+(:[A-Za-z0-9_@#%:]+:\s*$)`)
 
 func lexHeadline(line string) (token, bool) {
 	if m := headlineRegexp.FindStringSubmatch(line); m != nil {

org/inline.go

@@ -210,6 +210,9 @@ func (d *Document) parseRegularLink(input string, start int) (int, Node) {
 	if len(rawLinkParts) == 2 {
 		link, description = rawLinkParts[0], d.parseInline(rawLinkParts[1])
 	}
+	if strings.ContainsRune(link, '\n') {
+		return 0, nil
+	}
 	consumed := end + 2
 	protocol, linkParts := "", strings.SplitN(link, ":", 2)
 	if len(linkParts) == 2 {

org/org.go

@@ -3,6 +3,7 @@ package org
 import (
 	"fmt"
 	"strings"
+	"unicode/utf8"
 )
 
 type stringBuilder = strings.Builder
@@ -268,7 +269,7 @@ func (w *OrgWriter) writeTable(t Table) {
 				if content == "" {
 					content = " "
 				}
-				n := column.Len - len(content)
+				n := column.Len - utf8.RuneCountInString(content)
 				if n < 0 {
 					n = 0
 				}

org/table.go

@@ -4,6 +4,7 @@ import (
 	"regexp"
 	"strconv"
 	"strings"
+	"unicode/utf8"
 )
 
 type Table struct {
@@ -89,8 +90,8 @@ func getColumnInfos(rows [][]string) []ColumnInfo {
 				continue
 			}
 
-			if len(columns[i]) > columnInfos[i].Len {
+			if n := utf8.RuneCountInString(columns[i]); n > columnInfos[i].Len {
-				columnInfos[i].Len = len(columns[i])
+				columnInfos[i].Len = n
 			}
 
 			if m := columnAlignRegexp.FindStringSubmatch(columns[i]); m != nil && isSpecialRow(columns) {

org/testdata/tables.html

@@ -42,6 +42,42 @@ table with separator after header
 </figure>
 <figure>
 <table>
+<thead>
+<tr>
+<th>Character</th>
+<th>Org</th>
+<th>Rendered HTML</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Hyphen</td>
+<td><code class="verbatim">a - b</code></td>
+<td>a - b</td>
+</tr>
+<tr>
+<td>Ndash</td>
+<td><code class="verbatim">a -- b</code></td>
+<td>a – b</td>
+</tr>
+<tr>
+<td>Mdash</td>
+<td><code class="verbatim">a --- b</code></td>
+<td>a — b</td>
+</tr>
+<tr>
+<td>Ellipsis</td>
+<td><code class="verbatim">a ... b</code></td>
+<td>a … b</td>
+</tr>
+</tbody>
+</table>
+<figcaption>
+table with unicode characters
+</figcaption>
+</figure>
+<figure>
+<table>
 <tbody>
 <tr>
 <td class="align-right">1</td>

org/testdata/tables.org

@@ -9,6 +9,14 @@
 |---+---+---|
 | 1 | 2 | 3 |
 
+#+CAPTION: table with unicode characters
+| Character | Org       | Rendered HTML |
+|-----------+-----------+---------------|
+| Hyphen    | =a - b=   | a - b         |
+| Ndash     | =a -- b=  | a – b         |
+| Mdash     | =a --- b= | a — b         |
+| Ellipsis  | =a ... b= | a … b         |
+
 #+CAPTION: table without header (but separator before)
 |---+---+---|
 | 1 | 2 | 3 |

org/testdata/tables.pretty_org

@@ -9,6 +9,14 @@
 |---+---+---|
 | 1 | 2 | 3 |
 
+#+CAPTION: table with unicode characters
+| Character | Org       | Rendered HTML |
+|-----------+-----------+---------------|
+| Hyphen    | =a - b=   | a - b         |
+| Ndash     | =a -- b=  | a – b         |
+| Mdash     | =a --- b= | a — b         |
+| Ellipsis  | =a ... b= | a … b         |
+
 #+CAPTION: table without header (but separator before)
 |---+---+---|
 | 1 | 2 | 3 |