From b4721be4d543e1086c2309e1c571d737d0385d2e Mon Sep 17 00:00:00 2001
From: xinru1414 <xinru1414@gmail.com>
Date: Wed, 1 Jun 2022 09:49:48 -0700
Subject: [PATCH] Ingested UDFestBR 2022 (#1966)

* Added language tags
* Updated workflow to cancel previous build checks and preview generations (publication remains not-canceled)
* Moved from iso639 module to langcodes module (to support BCP-47)

Co-authored-by: Matt Post <mattpost@microsoft.com>
---
 .github/workflows/check-build.yml |  4 +-
 .github/workflows/preview.yml     |  4 +-
 bin/anthology/papers.py           |  6 +--
 bin/requirements.txt              |  2 +-
 data/xml/2022.udfestbr.xml        | 74 +++++++++++++++++++++++++++++++
 data/yaml/venues.yaml             |  3 ++
 6 files changed, 87 insertions(+), 6 deletions(-)
 create mode 100644 data/xml/2022.udfestbr.xml

diff --git a/.github/workflows/check-build.yml b/.github/workflows/check-build.yml
index bfff7d8797..6f5783a7aa 100644
--- a/.github/workflows/check-build.yml
+++ b/.github/workflows/check-build.yml
@@ -4,7 +4,9 @@ on:
   pull_request
 
 # only run one at a time per branch
-concurrency: check-build-${{ github.ref }}
+concurrency:
+  group: check-build-${{ github.ref }}
+  cancel-in-progress: true
 
 jobs:
   check-build:
diff --git a/.github/workflows/preview.yml b/.github/workflows/preview.yml
index 74a5a229b7..8874ab9074 100644
--- a/.github/workflows/preview.yml
+++ b/.github/workflows/preview.yml
@@ -10,7 +10,9 @@ on:
     - '!master'
 
 # only run one at a time per branch
-concurrency: preview-${{ github.ref }}
+concurrency:
+  group: preview-${{ github.ref }}
+  cancel-in-progress: true
 
 jobs:
   preview:
diff --git a/bin/anthology/papers.py b/bin/anthology/papers.py
index 989478b4c2..f39a7b7750 100644
--- a/bin/anthology/papers.py
+++ b/bin/anthology/papers.py
@@ -15,7 +15,7 @@
 # limitations under the License.
 
 from functools import cached_property
-import iso639
+import langcodes
 import logging as log
 
 from .utils import (
@@ -293,7 +293,7 @@ def isbn(self):
 
     @property
     def langcode(self):
-        """Returns the ISO-639 language code, if present"""
+        """Returns the BCP47 language code, if present"""
         return self.attrib.get("language", None)
 
     @property
@@ -301,7 +301,7 @@ def language(self):
         """Returns the language name, if present"""
         lang = None
         if self.langcode:
-            lang = iso639.languages.get(part3=self.langcode).name
+            lang = langcodes.Language.get(self.langcode).display_name()
         return lang
 
     def get(self, name, default=None):
diff --git a/bin/requirements.txt b/bin/requirements.txt
index 1096f39380..a05693cc85 100644
--- a/bin/requirements.txt
+++ b/bin/requirements.txt
@@ -4,7 +4,7 @@ citeproc-py-styles
 click
 docopt>=0.6.0
 filetype
-iso-639
+langcodes[data]
 latexcodec>=1.0.7
 lxml>=4.2.0
 nltk
diff --git a/data/xml/2022.udfestbr.xml b/data/xml/2022.udfestbr.xml
new file mode 100644
index 0000000000..07fdd24956
--- /dev/null
+++ b/data/xml/2022.udfestbr.xml
@@ -0,0 +1,74 @@
+<?xml version='1.0' encoding='UTF-8'?>
+<collection id="2022.udfestbr">
+  <volume id="1" ingest-date="2022-05-31">
+    <meta>
+      <booktitle>Procedings of the <fixed-case>U</fixed-case>niversal <fixed-case>D</fixed-case>ependencies <fixed-case>B</fixed-case>razilian Festival</booktitle>
+      <editor><first>Thiago Alexandre Salgueiro</first><last>Pardo</last></editor>
+      <editor><first>Ariani</first><last>Di-Felippo</last></editor>
+      <editor><first>Norton Trevisan</first><last>Roman</last></editor>
+      <publisher>Association for Computational Linguistics</publisher>
+      <address>Fortaleza, Brazil</address>
+      <month>march</month>
+      <year>2022</year>
+      <url hash="0ab16ffb">2022.udfestbr-1</url>
+    </meta>
+    <frontmatter>
+      <url hash="79abac39">2022.udfestbr-1.0</url>
+      <bibkey>udfestbr-2022-procedings</bibkey>
+    </frontmatter>
+    <paper id="1">
+      <title>Anotação de textos não canônicos: um estudo exploratorio de Grande sertão: veredas pelas dependências universais</title>
+      <language>pt-BR</language>
+      <author><first>Andre V. L.</first><last>Coneglian</last></author>
+      <author><first>Ana Luisa A. R.</first><last>Guimarães</last></author>
+      <author><first>Thiago Castro</first><last>Ferreira</last></author>
+      <author><first>Adriana S.</first><last>Pagano</last></author>
+      <pages>1–11</pages>
+      <url hash="8398b865">2022.udfestbr-1.1</url>
+      <bibkey>coneglian-etal-2022-anotacao</bibkey>
+    </paper>
+    <paper id="2">
+      <title>Polishing the gold – how much revision do we need in treebanks?</title>
+      <author><first>Elvis</first><last>Souza</last></author>
+      <author><first>Claudia</first><last>Freitas</last></author>
+      <pages>1–11</pages>
+      <url hash="c4709f4a">2022.udfestbr-1.2</url>
+      <bibkey>souza-freitas-2022-polishing</bibkey>
+    </paper>
+    <paper id="3">
+      <title>Que simples que nada: a anotação da palavra que em corpus de <fixed-case>UD</fixed-case></title>
+      <language>pt-BR</language>
+      <author><first>Magali S.</first><last>Duran</last></author>
+      <author><first>Heloisa</first><last>Oliveira</last></author>
+      <author><first>Clarissa</first><last>Scandarolli</last></author>
+      <pages>1–11</pages>
+      <url hash="b44fa3d0">2022.udfestbr-1.3</url>
+      <bibkey>duran-etal-2022-que</bibkey>
+    </paper>
+    <paper id="4">
+      <title>Shallow parsing of <fixed-case>P</fixed-case>ortuguese texts annotated under <fixed-case>U</fixed-case>niversal <fixed-case>D</fixed-case>ependencies</title>
+      <author><first>Guilherme Martiniano</first><last>Oliveira</last></author>
+      <author><first>Paulo Berlanga</first><last>Neto</last></author>
+      <author><first>Evandro Eduardo Seron</first><last>Ruiz</last></author>
+      <pages>1–8</pages>
+      <url hash="4ff0f086">2022.udfestbr-1.4</url>
+      <bibkey>oliveira-etal-2022-shallow</bibkey>
+    </paper>
+    <paper id="5">
+      <title>Still on arguments and adjuncts: the status of the indirect object and the adverbial adjunct relations in <fixed-case>U</fixed-case>niversal <fixed-case>D</fixed-case>ependencies for <fixed-case>P</fixed-case>ortuguese</title>
+      <author><first>Elvis</first><last>Souza</last></author>
+      <author><first>Claudia</first><last>Freitas</last></author>
+      <pages>1–10</pages>
+      <url hash="86c474fe">2022.udfestbr-1.5</url>
+      <bibkey>souza-freitas-2022-still</bibkey>
+    </paper>
+    <paper id="6">
+      <title><fixed-case>UDC</fixed-case>oncord: A Concordancer for <fixed-case>U</fixed-case>niversal <fixed-case>D</fixed-case>ependencies Treebanks</title>
+      <author><first>Lucas Gabriel Mendes</first><last>Miranda</last></author>
+      <author><first>Thiago Alexandre Salgueiro</first><last>Pardo</last></author>
+      <pages>1–10</pages>
+      <url hash="be1662f6">2022.udfestbr-1.6</url>
+      <bibkey>miranda-pardo-2022-udconcord</bibkey>
+    </paper>
+  </volume>
+</collection>
diff --git a/data/yaml/venues.yaml b/data/yaml/venues.yaml
index fc1c8c4571..198fb3e14d 100644
--- a/data/yaml/venues.yaml
+++ b/data/yaml/venues.yaml
@@ -1104,6 +1104,9 @@ tutorials:
   name: 'Proceedings of the 59th Annual Meeting of the Association for Computational
     Linguistics and the 11th International Joint Conference on Natural Language Processing:
     Tutorial Abstracts'
+udfestbr:
+  acronym: udfestbr
+  name: Universal Dependencies Brazilian Festival
 udw:
   acronym: UDW
   name: Universal Dependencies Workshop