From eeb083d3479806c53e0b5525f5dbbf64adb093e5 Mon Sep 17 00:00:00 2001
From: Celso Pinto <celso@celsopinto.com>
Date: Tue, 14 Apr 2026 20:05:16 +0800
Subject: [PATCH] Populate sender email and recipients in threads output

`hey threads <id> --json` was returning empty `creator.email_address`
and `recipients` for every entry because the HTML parser only captured
the sender's display name and ignored the rest of the sender link.

Scrape the sender email from the `<span class="entry__sender-email">`
inside each sender anchor, and extract per-entry recipients by slicing
the HTML between entry anchors and reusing the existing
`fullRecipientsRe` + `extractEmails` helpers. Dedupe recipients by
address so a repeat in the HTML doesn't produce duplicate contacts.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 internal/htmlutil/entries.go | 41 +++++++++++++++++++++++++++++++++++-
 1 file changed, 40 insertions(+), 1 deletion(-)

diff --git a/internal/htmlutil/entries.go b/internal/htmlutil/entries.go
index 70b3a4b..d0001b0 100644
--- a/internal/htmlutil/entries.go
+++ b/internal/htmlutil/entries.go
@@ -12,6 +12,7 @@ import (
 var (
 	entryBlockRe     = regexp.MustCompile(`(?s)data-entry-id="(\d+)"`)
 	senderRe         = regexp.MustCompile(`id="sender_entry_(\d+)"[^>]*>\s*([^<]+?)\s*<`)
+	senderEmailRe    = regexp.MustCompile(`(?s)sender_entry_(\d+).*?entry__sender-email[^>]*><span[^>]*>[^<]*</span>([^<]+)<`)
 	timeRe           = regexp.MustCompile(`<time[^>]*datetime="([^"]+)"`)
 	srcdocRe         = regexp.MustCompile(`(?s)srcdoc="([^"]*trix-content[^"]*)"`)
 	fullRecipientsRe = regexp.MustCompile(`(?s)entry__full-recipients[^>]*>(.*?)</span>`)
@@ -86,6 +87,12 @@ func ParseTopicEntriesHTML(html string) []models.Entry {
 			senders[m[1]] = m[2]
 		}
 	}
+	senderEmails := map[string]string{}
+	for _, m := range senderEmailRe.FindAllStringSubmatch(html, -1) {
+		if _, exists := senderEmails[m[1]]; !exists {
+			senderEmails[m[1]] = strings.TrimSpace(m[2])
+		}
+	}
 
 	// Associate times with entries by finding the first <time> after each entry anchor
 	entryTimes := map[string]string{}
@@ -100,6 +107,35 @@ func ParseTopicEntriesHTML(html string) []models.Entry {
 		}
 	}
 
+	// Associate recipients with entries by slicing between entry anchors.
+	entryRecipients := map[string][]models.Contact{}
+	for i, eid := range entryIDs {
+		anchor := fmt.Sprintf(`id="entry_%s"`, eid)
+		start := strings.Index(html, anchor)
+		if start < 0 {
+			continue
+		}
+		end := len(html)
+		if i+1 < len(entryIDs) {
+			nextAnchor := fmt.Sprintf(`id="entry_%s"`, entryIDs[i+1])
+			if n := strings.Index(html[start:], nextAnchor); n > 0 {
+				end = start + n
+			}
+		}
+		m := fullRecipientsRe.FindStringSubmatch(html[start:end])
+		if m == nil {
+			continue
+		}
+		seen := map[string]bool{}
+		for _, addr := range extractEmails(m[1]) {
+			if seen[addr] {
+				continue
+			}
+			seen[addr] = true
+			entryRecipients[eid] = append(entryRecipients[eid], models.Contact{EmailAddress: addr})
+		}
+	}
+
 	// Extract bodies from srcdoc iframes - they appear in entry order
 	type body struct{ html, text string }
 	bodyMatches := srcdocRe.FindAllStringSubmatch(html, -1)
@@ -122,7 +158,10 @@ func ParseTopicEntriesHTML(html string) []models.Entry {
 			CreatedAt: entryTimes[eid],
 		}
 		if name, ok := senders[eid]; ok {
-			e.Creator = models.Contact{Name: name}
+			e.Creator = models.Contact{Name: name, EmailAddress: senderEmails[eid]}
+		}
+		if recips, ok := entryRecipients[eid]; ok {
+			e.Recipients = recips
 		}
 		if i < len(bodies) {
 			e.Body = bodies[i].text