fix(JATS): Do not duplicate ListItems when decoding nested lists

See elifesciences/enhanced-preprints-issues#647
stencila · May 22, 2023 · abb3a18 · abb3a18
1 parent a08cfb7
commit abb3a18
Show file tree

Hide file tree

Showing 7 changed files with 171 additions and 30 deletions.
diff --git a/src/codecs/jats/__file_snapshots__/f1000-7-1655-v1.jats.xml b/src/codecs/jats/__file_snapshots__/f1000-7-1655-v1.jats.xml
@@ -293,15 +293,6 @@
                         </list-item>
                     </list>
                 </list-item>
-                <list-item>
-                    <p>Reviewing the content for sensitive information, e.g., unpublished data additions and confidentiality leaks, as well ensuring the tone of the report is appropriate</p>
-                </list-item>
-                <list-item>
-                    <p>Removing author responses that contain data the author wants to publish in a subsequent paper</p>
-                </list-item>
-                <list-item>
-                    <p>Arbitration processes for conflicting reviews</p>
-                </list-item>
             </list>
             <p>Where time is spent—whether in the editorial or production process—depends on the publisher workflow. Regardless of workflow, the overlap in tasks identified provides evidence of the potential value of updating the infrastructure of submission systems to account for and streamline these efforts. Coordination between publishers and submission systems could minimize the time spent “stitching together” peer review materials into a publishable format.</p>
             <p>In addition to time and workflow hurdles, another major challenge noted by those publishers without their own hosting platforms, was the actual publication process and online hosting of peer review materials. Many publishers identified that some online hosts were not able to manage this new content type. As a result, peer review materials are being captured in supplementary material sections because alternative options are not available. In such cases, it becomes more difficult to capture any relevant associated metadata in a meaningful way for the peer review materials or to make this valuable content easily discoverable.</p>

diff --git a/src/codecs/jats/__file_snapshots__/f1000-7-1655-v1.yaml b/src/codecs/jats/__file_snapshots__/f1000-7-1655-v1.yaml
@@ -682,26 +682,6 @@ content:
             order: Unordered
             meta:
               listType: bullet
-      - type: ListItem
-        content:
-          - type: Paragraph
-            content:
-              - >-
-                Reviewing the content for sensitive information, e.g.,
-                unpublished data additions and confidentiality leaks, as well
-                ensuring the tone of the report is appropriate
-      - type: ListItem
-        content:
-          - type: Paragraph
-            content:
-              - >-
-                Removing author responses that contain data the author wants to
-                publish in a subsequent paper
-      - type: ListItem
-        content:
-          - type: Paragraph
-            content:
-              - Arbitration processes for conflicting reviews
     order: Unordered
     meta:
       listType: bullet

diff --git a/src/codecs/jats/__file_snapshots__/nested-list.jats.xml b/src/codecs/jats/__file_snapshots__/nested-list.jats.xml
@@ -0,0 +1,58 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.1 20151215//EN" "JATS-archivearticle1.dtd">
+<article xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article">
+    <front>
+        <article-meta>
+            <title-group>
+                <article-title>Untitled</article-title>
+            </title-group>
+            <contrib-group/>
+        </article-meta>
+    </front>
+    <body>
+        <sec>
+            <list list-type="bullet">
+                <list-item>
+                    <p>A</p>
+                </list-item>
+                <list-item>
+                    <p>B
+                </p>
+                    <list list-type="bullet">
+                        <list-item>
+                            <p>B1</p>
+                        </list-item>
+                        <list-item>
+                            <p>B2</p>
+                        </list-item>
+                        <list-item>
+                            <p>B3</p>
+                        </list-item>
+                    </list>
+                </list-item>
+                <list-item>
+                    <p>C</p>
+                </list-item>
+                <list-item>
+                    <p>D
+                </p>
+                    <list list-type="bullet">
+                        <list-item>
+                            <p>D1</p>
+                        </list-item>
+                        <list-item>
+                            <p>D2</p>
+                        </list-item>
+                        <list-item>
+                            <p>D3</p>
+                        </list-item>
+                    </list>
+                </list-item>
+                <list-item>
+                    <p>E</p>
+                </list-item>
+            </list>
+        </sec>
+    </body>
+    <back/>
+</article>
diff --git a/src/codecs/jats/__file_snapshots__/nested-list.yaml b/src/codecs/jats/__file_snapshots__/nested-list.yaml
@@ -0,0 +1,79 @@
+type: Article
+identifiers: []
+title: Untitled
+meta: {}
+content:
+  - type: List
+    items:
+      - type: ListItem
+        content:
+          - type: Paragraph
+            content:
+              - A
+      - type: ListItem
+        content:
+          - type: Paragraph
+            content:
+              - |-
+                B
+                                
+          - type: List
+            items:
+              - type: ListItem
+                content:
+                  - type: Paragraph
+                    content:
+                      - B1
+              - type: ListItem
+                content:
+                  - type: Paragraph
+                    content:
+                      - B2
+              - type: ListItem
+                content:
+                  - type: Paragraph
+                    content:
+                      - B3
+            order: Unordered
+            meta:
+              listType: bullet
+      - type: ListItem
+        content:
+          - type: Paragraph
+            content:
+              - C
+      - type: ListItem
+        content:
+          - type: Paragraph
+            content:
+              - |-
+                D
+                                
+          - type: List
+            items:
+              - type: ListItem
+                content:
+                  - type: Paragraph
+                    content:
+                      - D1
+              - type: ListItem
+                content:
+                  - type: Paragraph
+                    content:
+                      - D2
+              - type: ListItem
+                content:
+                  - type: Paragraph
+                    content:
+                      - D3
+            order: Unordered
+            meta:
+              listType: bullet
+      - type: ListItem
+        content:
+          - type: Paragraph
+            content:
+              - E
+    order: Unordered
+    meta:
+      listType: bullet
diff --git a/src/codecs/jats/__fixtures__/nested-list.xml b/src/codecs/jats/__fixtures__/nested-list.xml
@@ -0,0 +1,32 @@
+<?xml version="1.0"?>
+<article>
+    <front>
+        <article-meta>
+            <contrib-group />
+        </article-meta>
+    </front>
+    <body>
+        <list list-type="bullet">
+            <list-item><p>A</p></list-item>
+            <list-item><p>B
+                <list list-type="bullet">
+                    <list-item><p>B1</p></list-item>
+                    <list-item><p>B2</p></list-item>
+                    <list-item><p>B3</p></list-item>
+                </list>
+            </p></list-item>
+            <list-item><p>C</p></list-item>
+            <list-item><p>D
+                <list list-type="bullet">
+                    <list-item><p>D1</p></list-item>
+                    <list-item><p>D2</p></list-item>
+                    <list-item><p>D3</p></list-item>
+                </list>
+                </p></list-item>
+            <list-item><p>E</p></list-item>
+        </list>
+    </body>
+    <back>
+        <app-group />
+    </back>
+</article>
diff --git a/src/codecs/jats/index.ts b/src/codecs/jats/index.ts
@@ -2095,7 +2095,7 @@ function decodeList(elem: xml.Element, state: DecodeState): [stencila.List] {
   const type = attr(elem, 'list-type')
   const order =
     type === 'bullet' || type === 'simple' ? 'Unordered' : 'Ascending'
-  const items = all(elem, 'list-item').map((item): stencila.ListItem => {
+  const items = children(elem, 'list-item').map((item): stencila.ListItem => {
     return stencila.listItem({
       content: ensureBlockContentArray(
         decodeElements(item.elements ?? [], state)

diff --git a/src/codecs/jats/jats.test.ts b/src/codecs/jats/jats.test.ts
@@ -291,6 +291,7 @@ test.each([
   'fig.xml',
   'statement.xml',
   'quote.xml',
+  'nested-list.xml',
   'elife-30274-v1',
   'elife-43154-v2',
   'elife-46472-v3',