parseMail: add support for mbox

Add support for reading email from an mbox.

Author: ferdinandyb

README.md

@@ -1,15 +1,16 @@
 # Description
 
-Generates a ranked addressbook from a maildir (or similar one-mail-per-file)
-folder. It can be used in MUA's like [aerc](http://aerc-mail.org) or
-[mutt](http://www.mutt.org/) by grepping the list.
+Generates a ranked addressbook from your locally available email. It can be
+used in MUA's like [aerc](http://aerc-mail.org) or [mutt](http://www.mutt.org/)
+by grepping the list.
 
 Why? No need to manually edit an address book, yet the cached ranking is
 available extremely fast.
 
 ### Features:
 
 - scans all your emails
+- support maildir or similar one-email-per-file formats, and mbox
 - ranks based on both recency and frequency of addresses
 - collects from To, Cc, Bcc, From, Sender and Reply-To fields
 - ranks addresses explicitly emailed by you higher
@@ -63,9 +64,9 @@ Supported flags:
 **maildir**
 
 The paths to the folders that will be scanned. No default is set for this.
-These actually do NOT need to be maildir format folders, it only assumes that
-each file is an email (it will skip any hidden files and anything that is in
-a folder called `tmp`).
+These actually do NOT need to be maildir format folders, it will try to read
+all files as an email or an mbox (it will skip any hidden files and anything
+that is in a folder called `tmp` or `.notmuch`).
 
 **outputpath**
 

e2e_test.go

@@ -282,3 +282,13 @@ func TestE2EListTemplateDisable(t *testing.T) {
 		})
 	}
 }
+
+func TestE2EMbox(t *testing.T) {
+	data := walkSources(
+		[]string{"./testdata/endtoend"},
+		[]*regexp.Regexp{regexp.MustCompile("[email protected]")},
+		nil,
+	)
+	classeddata := calculateRanks(data, nil, nil)
+	assert.Contains(t, classeddata[0], "[email protected]")
+}

go.mod

@@ -5,6 +5,7 @@ go 1.22.0
 toolchain go1.23.4
 
 require (
+	github.com/emersion/go-mbox v1.0.3
 	github.com/emersion/go-message v0.18.2
 	github.com/mitchellh/go-homedir v1.1.0
 	github.com/spf13/pflag v1.0.5

go.sum

@@ -1,6 +1,8 @@
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/emersion/go-mbox v1.0.3 h1:Kac75r/EGi6KZAz48HXal9q7EiaXNl+U5HZfyDz0LKM=
+github.com/emersion/go-mbox v1.0.3/go.mod h1:Yp9IVuuOYLEuMv4yjgDHvhb5mHOcYH6x92Oas3QqEZI=
 github.com/emersion/go-message v0.18.2 h1:rl55SQdjd9oJcIoQNhubD2Acs1E6IzlZISRTK7x/Lpg=
 github.com/emersion/go-message v0.18.2/go.mod h1:XpJyL70LwRvq2a8rVbHXikPgKj8+aI0kGdHlg16ibYA=
 github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHkI4W8=

parseMail.go

@@ -1,7 +1,9 @@
 package main
 
 import (
+	"errors"
 	"fmt"
+	"io"
 	"mime"
 	"os"
 	"path/filepath"
@@ -11,10 +13,33 @@ import (
 	"sync"
 	"unicode/utf8"
 
+	"github.com/emersion/go-mbox"
+	"github.com/emersion/go-message"
 	_ "github.com/emersion/go-message/charset"
 	"github.com/emersion/go-message/mail"
 )
 
+func mboxParser(path string, headers chan<- *mail.Header) error {
+	f, err := os.Open(path)
+	defer f.Close()
+	if err != nil {
+		return err
+	}
+	mbr := mbox.NewReader(f)
+	for {
+		msg, err := mbr.NextMessage()
+		if errors.Is(err, io.EOF) {
+			break
+		} else if err != nil {
+			return err
+		}
+		entity, err := message.Read(msg)
+		h := &mail.Header{Header: entity.Header}
+		headers <- h
+	}
+	return nil
+}
+
 func messageParser(
 	paths chan string,
 	headers chan<- *mail.Header,
@@ -28,6 +53,10 @@ func messageParser(
 		}
 		r, err := mail.CreateReader(f)
 		if err != nil {
+			mboxerr := mboxParser(path, headers)
+			if mboxerr == nil {
+				continue
+			}
 			if utf8.ValidString(err.Error()) {
 				fmt.Fprintln(os.Stderr, path, err)
 			} else {