Duplicate of #2744 in order to generate a preview

.pre-commit-config.yaml

@@ -6,7 +6,11 @@ repos:
     - id: check-ast
     - id: check-merge-conflict
     - id: check-xml
-      exclude: ^hugo/layouts/sitemap.xml$
+      exclude: |
+          (?x)^(
+              hugo/layouts/sitemap.xml|
+              hugo/layouts/_default/rss.xml
+          )$
     - id: check-yaml
       exclude: ^python/mkdocs.yml$
     - id: end-of-file-fixer

bin/create_hugo_pages.py

@@ -84,9 +84,14 @@ def create_papers(srcdir, clean=False):
             if not os.path.exists(paper_dir):
                 os.makedirs(paper_dir)
             with open("{}/{}.md".format(paper_dir, anthology_id), "w") as f:
+                date = entry["ingest_date"]
                 print("---", file=f)
                 yaml.dump(
-                    {"anthology_id": anthology_id, "title": entry["title"]},
+                    {
+                        "anthology_id": anthology_id,
+                        "title": entry["title"],
+                        "date": date,
+                    },
                     default_flow_style=False,
                     stream=f,
                 )

bin/create_hugo_yaml.py

@@ -64,6 +64,8 @@ def export_anthology(anthology, outdir, clean=False, dryrun=False):
     for id_, paper in anthology.papers.items():
         log.debug("export_anthology: processing paper '{}'".format(id_))
         data = paper.as_dict()
+        if paper.parent_volume.ingest_date:
+            data["ingest_date"] = paper.parent_volume.ingest_date
         data["title_html"] = paper.get_title("html")
         if "xml_title" in data:
             del data["xml_title"]

hugo/config.toml

@@ -2,6 +2,7 @@ languageCode = "en-us"
 title = "ACL Anthology"
 disablePathToLower = true
 staticDir = ["static", "data-export"]
+rssLimit = 1000
 
 [permalinks]
   papers = "/:filename/"

hugo/content/posts/_index.md

@@ -1,4 +1,4 @@
 ---
-Title: List of all posts
+Title: List of all news pages
 render_pagelist: true
 ---

hugo/content/posts/announce_news.md

@@ -0,0 +1,18 @@
+---
+Title: New page for announcements and blog posts
+date: "2024-05-06"
+Description: >
+    The ACL Anthology website now has a dedicated section for blog posts and announcements as well as an RSS feed for papers. 🎉
+---
+
+The ACL Anthology website now has a dedicated section for blog posts and announcements.
+If you want to stay up to date on the most important changes to the Anthology, you can subscribe to the [RSS feed for this section](/posts/index.xml).
+
+We will keep the [existing mailing list](http://groups.google.com/group/acl-anthology?hl=en), so you will still get your updates if you are already subscribed.
+This new section mainly makes our updates available to more apps and devices via RSS, and it gives them a more appealing look. ✨
+
+There is one more thing that we want to announce with this post: We now also have an [RSS feed for papers](/papers/index.xml).
+By subscribing to this, you get to see the individual papers added to the Anthology and never miss any of the latest developments in NLP and computational linguistics ever again! 🎉
+The feed is limited to the latest 1000 papers, as the full file would be over 40 MB in size, otherwise. 🤯
+
+We hope that you will enjoy these new features as much as we do, and we'll see you here for the next update!

hugo/layouts/_default/index_flex.html

@@ -13,7 +13,7 @@ <h2 id="title" class="ml-2">Welcome to the ACL Anthology</h2>
           The ACL Anthology currently hosts {{ $.Scratch.Get "paper_count" }} papers on the study of computational linguistics and natural language processing.
         </div>
         <div class="card-body">
-          <a href="http://groups.google.com/group/acl-anthology?hl=en">Subscribe to the mailing list</a> to receive announcements and updates to the Anthology.
+          <a href="http://groups.google.com/group/acl-anthology?hl=en">Subscribe to the mailing list</a> or the <a href="{{ "posts/index.xml" | relURL }}">RSS news feed</a> to receive announcements and updates to the Anthology.
         </div>
       </aside>
     </div>

hugo/layouts/_default/rss.xml

@@ -0,0 +1,63 @@
+{{- $pctx := . -}}
+{{- if .IsHome -}}{{ $pctx = .Site }}{{- end -}}
+{{- $pages := slice -}}
+{{- if or $.IsHome $.IsSection -}}
+  {{- $pages = $pctx.RegularPages -}}
+{{- else -}}
+  {{- $pages = $pctx.Pages -}}
+{{- end -}}
+{{- $limit := .Site.Config.Services.RSS.Limit -}}
+{{- if ge $limit 1 -}}
+  <!-- First get the last page that we *would* render given the rssLimit. -->
+  {{- $last_page := (sort $pages "Date" "desc") | first $limit | last 1 -}}
+  {{- $last_page = (index $last_page 0) -}}
+  <!-- Then re-do the selection by date, including all pages with the same date as the last entry. -->
+  {{- $pages = (sort (where $pages "Date" ">=" $last_page.Date) "Date" "desc") -}}
+{{- end -}}
+{{- printf "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"yes\"?>" | safeHTML }}
+<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
+  <channel>
+    <title>{{ if eq  .Title  .Site.Title }}{{ .Site.Title }}{{ else }}{{ with .Title }}{{.}} on {{ end }}{{ .Site.Title }}{{ end }}</title>
+    <link>{{ .Permalink }}</link>
+    <description>Recent content {{ if ne  .Title  .Site.Title }}{{ with .Title }}in {{.}} {{ end }}{{ end }}on {{ .Site.Title }}</description>
+    <generator>Hugo -- gohugo.io</generator>
+    <language>{{ site.LanguageCode }}</language>{{ with .Site.Author.email }}
+    <managingEditor>{{.}}{{ with $.Site.Author.name }} ({{.}}){{end}}</managingEditor>{{end}}{{ with .Site.Author.email }}
+    <webMaster>{{.}}{{ with $.Site.Author.name }} ({{.}}){{end}}</webMaster>{{end}}{{ with .Site.Copyright }}
+    <copyright>{{.}}</copyright>{{end}}{{ if not .Date.IsZero }}
+    <lastBuildDate>{{ .Date.Format "Mon, 02 Jan 2006 15:04:05 -0700" | safeHTML }}</lastBuildDate>{{ end }}
+    {{- with .OutputFormats.Get "RSS" -}}
+    {{ printf "<atom:link href=%q rel=\"self\" type=%q />" .Permalink .MediaType | safeHTML }}
+    {{- end -}}
+    {{ range $pages }}
+    <item>
+      <title>{{ .Title }}</title>
+      <link>{{ .Permalink }}</link>
+      <pubDate>{{ .Date.Format "Mon, 02 Jan 2006 15:04:05 -0700" | safeHTML }}</pubDate>
+      <guid><!-- Prefer anthology id if it exists, use permalink otherwise. -->
+        {{- if isset .Params "anthology_id" -}}
+          {{- .Param "anthology_id" -}}
+        {{- else -}}
+          {{- .Permalink -}}
+        {{- end -}}
+      </guid>
+      <description>
+        {{- if isset .Params "anthology_id" -}}
+          {{- $volume_id := index (split .Params.anthology_id "-") 0 -}}
+          {{- $paper := index (index $.Site.Data.papers $volume_id) .Params.anthology_id -}}
+          {{- with $paper.author -}}
+            {{- delimit (apply $paper.author "index" "." "full") ", " " and " -}}
+          {{- end -}}
+          {{- $volume_nr := index (split (index (split .Params.anthology_id "-") 1) ".") 0 -}}
+          {{- $volume := index $.Site.Data.volumes (printf "%s-%s" $volume_id $volume_nr) -}}
+          {{- printf " in %s" $volume.title -}}
+        {{- else if .Description -}}
+          {{ .Description | html }}
+        {{- else -}}
+          {{ .Summary | html }}
+        {{- end -}}
+      </description>
+    </item>
+    {{ end }}
+  </channel>
+</rss>

hugo/layouts/index.html

@@ -15,6 +15,10 @@
 </script>
 {{ end }}
 
+{{ define "meta" }}
+    <link rel="alternate" type="application/rss+xml" href="{{ "papers/index.xml" | relURL }}" title="ACL Anthology Papers" />
+{{ end }}
+
 {{ define "main" }}
 <div class="row justify-content-center">
   {{ $.Scratch.Set "paper_count" 0 }}
@@ -30,7 +34,7 @@ <h2 class="pl-2 pb-2">Welcome to the ACL Anthology!</h2>
         The ACL Anthology currently hosts {{ $.Scratch.Get "paper_count" }} papers on the study of computational linguistics and natural language processing.
       </div>
       <div class="card-body">
-        <a href="http://groups.google.com/group/acl-anthology?hl=en">Subscribe to the mailing list</a> to receive announcements and updates to the Anthology.
+        <a href="http://groups.google.com/group/acl-anthology?hl=en">Subscribe to the mailing list</a> or the <a href="{{ "posts/index.xml" | relURL }}">RSS news feed</a> to receive announcements and updates to the Anthology.
       </div>
     </aside>
 
@@ -47,12 +51,15 @@ <h2 class="pl-2 pb-2">Welcome to the ACL Anthology!</h2>
     <div class="row mb-3">
       {{ if (fileExists "/data-export/anthology.bib.gz") }}
       <div class="col-6 col-xl-12 mb-2">
-        <a class="btn btn-block btn-info" href="{{ "/anthology.bib.gz" | relURL }}">Full Anthology as BibTeX ({{ printf "%.2f MB" (div (os.Stat "/data-export/anthology.bib.gz").Size 1000000.0) }})</a>
-        <a class="btn btn-block btn-info" href="{{ "/anthology+abstracts.bib.gz" | relURL }}">…with abstracts ({{ printf "%.2f MB" (div (os.Stat "/data-export/anthology+abstracts.bib.gz").Size 1000000.0) }})</a>
+        <a class="btn btn-block btn-info" href="{{ "anthology.bib.gz" | relURL }}">Full Anthology as BibTeX ({{ printf "%.2f MB" (div (os.Stat "/data-export/anthology.bib.gz").Size 1000000.0) }})</a>
+        <a class="btn btn-block btn-info" href="{{ "anthology+abstracts.bib.gz" | relURL }}">…with abstracts ({{ printf "%.2f MB" (div (os.Stat "/data-export/anthology+abstracts.bib.gz").Size 1000000.0) }})</a>
       </div>
       {{ end }}
       <div class="col-6 col-xl-12 mb-2">
-        <a class="btn btn-block btn-warning" href="{{ ($.Site.GetPage "/faq/feedback.md").RelPermalink }}">Give feedback</a>
+        <a class="btn btn-block btn-warning" href="{{ "papers/index.xml" | relURL }}">RSS Feed (latest 1000 papers)</a>
+      </div>
+      <div class="col-6 col-xl-12 mb-2">
+        <a class="btn btn-block btn-success" href="{{ ($.Site.GetPage "/faq/feedback.md").RelPermalink }}">Give feedback</a>
       </div>
     </div>
   </div><div class="col-12 col-xl-10 col-xl-width-auto">

hugo/layouts/partials/header_navbar.html

@@ -10,6 +10,9 @@
 
   <div class="collapse navbar-collapse" id="navbarSupportedContent">
     <ul class="navbar-nav flex-grow-1 pr-md-2">
+      <li class="nav-item">
+        <a class="nav-link" href={{ relref . "/posts" }}>News<span class="sr-only">(current)</span></a>
+      </li>
       <li class="nav-item">
         <a class="nav-link" href={{ relref . "/faq" }}>FAQ<span class="sr-only">(current)</span></a>
       </li>

hugo/layouts/posts/list.html

@@ -0,0 +1,26 @@
+{{ define "main" }}
+<main>
+    <article>
+        <header>
+            <h1>{{.Title}}</h1>
+        </header>
+        <!-- "{{.Content}}" pulls from the markdown content of the corresponding _index.md -->
+        {{.Content}}
+    </article>
+    <ul>
+    <!-- Ranges through content/posts/*.md -->
+    {{ range .Pages.ByDate.Reverse }}
+        <li>
+            <a href="{{.Permalink}}">{{.Date.Format "2006-01-02"}} | {{.Title}}</a>
+            <p><small>
+            {{- if .Description -}}
+                {{ .Description }}
+            {{- else -}}
+                {{ .Summary }}...
+            {{- end -}}
+            </small></p>
+        </li>
+    {{ end }}
+    </ul>
+</main>
+{{ end }}