feat: abstract doesn't directly state it updates or obsoletes each do…

…cument so affected (#71) * feat: added validation for obsoletes and updates - added validation for update and obsolete metadata - added validation for obsolete and updated rfc in abstract - tested app covered new validation with tests - modified abstract section validation * feat: added tests for obsolete and update metadata parsing * fix: corrected test header Co-authored-by: Robert Sparks <rjsparks@nostrum.com> --------- Co-authored-by: Robert Sparks <rjsparks@nostrum.com>
ietf-tools · Feb 21, 2025 · f5fb8ec · f5fb8ec
1 parent 7e58021
commit f5fb8ec
Show file tree

Hide file tree

Showing 6 changed files with 398 additions and 9 deletions.
diff --git a/lib/modules/metadata.mjs b/lib/modules/metadata.mjs
@@ -1,4 +1,4 @@
-import { ValidationWarning } from '../helpers/error.mjs'
+import { ValidationComment, ValidationWarning } from '../helpers/error.mjs'
 import { traverseAllValues } from '../helpers/traversal.mjs'
 import { fetchRemoteDocInfo, fetchRemoteRfcInfo } from '../helpers/remote.mjs'
 import { MODES } from '../config/modes.mjs'
@@ -115,7 +115,65 @@ export async function validateObsoleteUpdateRef (doc, { mode = MODES.NORMAL, off
 
   switch (doc.type) {
     case 'txt': {
-      // TODO: Text type validation
+      const abstract = doc.data.content.abstract.join(' ') || ''
+      const obsoletesRfc = doc.data.extractedElements.obsoletesRfc
+      const updatesRfc = doc.data.extractedElements.updatesRfc
+
+      const mentionedObsoletesRfcs = [...abstract.matchAll(OBSOLETES_RE)]
+        .flatMap(match => (match[0].match(RFC_NUM_RE) || []))
+      const mentionedUpdatesRfcs = [...abstract.matchAll(UPDATES_RE)]
+        .flatMap(match => (match[0].match(RFC_NUM_RE) || []))
+
+      // RFCs in obsoletes/updates but not mentioned in abstract
+      const obsoletesNotInAbstract = obsoletesRfc.filter(rfc => !mentionedObsoletesRfcs.includes(rfc))
+      const updatesNotInAbstract = updatesRfc.filter(rfc => !mentionedUpdatesRfcs.includes(rfc))
+
+      obsoletesNotInAbstract.forEach(rfc => {
+        result.push(new ValidationComment(
+          'OBSOLETES_NOT_IN_ABSTRACT',
+          `RFC ${rfc} is listed as "obsoleted" in metadata but is not mentioned in the abstract.`,
+          {
+            ref: 'https://authors.ietf.org/en/required-content#abstract',
+            path: 'data.content.abstract'
+          }
+        ))
+      })
+
+      updatesNotInAbstract.forEach(rfc => {
+        result.push(new ValidationComment(
+          'UPDATES_NOT_IN_ABSTRACT',
+          `RFC ${rfc} is listed as "updated" in metadata but is not mentioned in the abstract.`,
+          {
+            ref: 'https://authors.ietf.org/en/required-content#abstract',
+            path: 'data.content.abstract'
+          }
+        ))
+      })
+
+      const mentionedButNotObsoletes = mentionedObsoletesRfcs.filter(rfc => !obsoletesRfc.includes(rfc))
+      const mentionedButNotUpdates = mentionedUpdatesRfcs.filter(rfc => !updatesRfc.includes(rfc))
+
+      mentionedButNotObsoletes.forEach(rfc => {
+        result.push(new ValidationComment(
+          'MENTIONED_NOT_IN_OBSOLETES',
+          `RFC ${rfc} is mentioned as "obsoleted" or "replaced" in the abstract but not listed in metadata.`,
+          {
+            ref: 'https://authors.ietf.org/en/required-content#abstract',
+            path: 'data.content.abstract'
+          }
+        ))
+      })
+
+      mentionedButNotUpdates.forEach(rfc => {
+        result.push(new ValidationComment(
+          'MENTIONED_NOT_IN_UPDATES',
+          `RFC ${rfc} is mentioned as "updated" in the abstract but not listed in metadata.`,
+          {
+            ref: 'https://authors.ietf.org/en/required-content#abstract',
+            path: 'data.content.abstract'
+          }
+        ))
+      })
       break
     }
     case 'xml': {

diff --git a/lib/modules/sections.mjs b/lib/modules/sections.mjs
@@ -26,13 +26,18 @@ export async function validateAbstractSection (doc, { mode = MODES.NORMAL } = {}
           ref: 'https://authors.ietf.org/required-content#abstract'
         }))
       } else {
-        const abstractContent = doc.data.content.abstract.join(' ')
+        const abstractContent = doc.data.content.abstract.join(' ') || ''
+        const updatesRfc = doc.data.extractedElements?.updatesRfc || []
+        const obsoletesRfc = doc.data.extractedElements?.obsoletesRfc || []
 
-        const rfcReferencePattern = /\[RFC\d+\]/i
+        const rfcReferencePattern = /\[RFC\d+\]/ig
         const urlPattern = /https?:\/\/[^\s]+|www\.[^\s]+/i
         const sectionReferencePattern = /\bSection\s\d+(\.\d+)?\b|\bAppendix\s\w+\b/i
         const internetDraftReferencePattern = /\[I-D\.[^\]]+\]/i
-        const customReferencePattern = /\[[A-Za-z0-9-]+\]/i
+        const customReferencePattern = /\[(?!RFC\d+\b)[A-Za-z0-9-]+\]/i
+
+        const rfcMatches = [...abstractContent.matchAll(rfcReferencePattern)].map(match => match[0].match(/\d+/)[0])
+        const notAllowedRfcReferences = rfcMatches.filter(rfc => !updatesRfc.includes(rfc) && !obsoletesRfc.includes(rfc))
 
         const validateReference = (pattern, errorCode, errorMessage) => {
           if (pattern.test(abstractContent)) {
@@ -53,7 +58,7 @@ export async function validateAbstractSection (doc, { mode = MODES.NORMAL } = {}
           }
         }
 
-        validateReference(rfcReferencePattern, 'INVALID_ABSTRACT_SECTION_REF', 'The abstract section should not contain references to RFCs.')
+        if (notAllowedRfcReferences.length > 0) validateReference(rfcReferencePattern, 'INVALID_ABSTRACT_SECTION_REF', 'The abstract section should not contain references to RFCs.')
         validateReference(urlPattern, 'INVALID_ABSTRACT_SECTION_URL', 'The abstract section should not contain URLs.')
         validateReference(sectionReferencePattern, 'INVALID_ABSTRACT_SECTION_REF', 'The abstract section should not contain references to sections or appendices.')
         validateReference(internetDraftReferencePattern, 'INVALID_ABSTRACT_SECTION_ID_REF', 'The abstract section should not contain references to Internet-Drafts.')

diff --git a/lib/parsers/txt.mjs b/lib/parsers/txt.mjs
@@ -78,6 +78,10 @@ const KEYWORDS_PATTERN = /((NOT)\s)?(MUST|REQUIRED|SHALL|SHOULD|RECOMMENDED|OPTI
 // Invalid combinations regex pattern
 const INVALID_COMBINATIONS_PATTERN = /(MUST not|SHALL not|SHOULD not|not RECOMMENDED|MAY NOT|NOT REQUIRED|NOT OPTIONAL)/g
 
+// Obsolete and updates regex patterns
+const OBSOLETES_RE = /(?:obsoletes|replaces)\s*:\s*((?:rfc\s*)?[0-9]+(?:,|\s|and)*\s*)+/gi
+const UPDATES_RE = /updates\s*:\s*((?:rfc\s*)?[0-9]+(?:,|\s|and)*\s*)+/gi
+
 /**
  * @typedef {Object} TXTDocObject
  * @property {Object} data Parsed TXT tree
@@ -124,7 +128,9 @@ export async function parse (rawText, filename) {
       ipv4: [],
       ipv6: [],
       keywords2119: [],
-      boilerplate2119Keywords: []
+      boilerplate2119Keywords: [],
+      obsoletesRfc: [],
+      updatesRfc: []
     },
     boilerplate: {
       rfc2119: BOILERPLATE_PATTERNS.rfc2119.test(normalizedText) || BOILERPLATE_PATTERNS.rfc2119_alt.test(normalizedText),
@@ -169,6 +175,12 @@ export async function parse (rawText, filename) {
     data.boilerplate.similar2119boilerplate =
       hasBoilerplateMatch(normalizedText, BOILERPLATE_PARTS.rfc2119, BOILERPLATE_PARTS.rfc2119_alt, BOILERPLATE_PARTS.rfc8174) && !(data.boilerplate.rfc2119 || data.boilerplate.rfc8174)
 
+    const obsoletesRfcs = extractRfcNumbers(normalizedText, OBSOLETES_RE)
+    data.extractedElements.obsoletesRfc.push(...obsoletesRfcs.plainNumbers)
+
+    const updatesRfcs = extractRfcNumbers(normalizedText, UPDATES_RE)
+    data.extractedElements.updatesRfc.push(...updatesRfcs.plainNumbers)
+
     for (const line of rawText.split('\n')) {
       const trimmedLine = line.trim()
       lineIdx++
@@ -459,3 +471,37 @@ function hasBoilerplateMatch (text, ...regexGroups) {
   }
   return false
 }
+
+/**
+ * Extract RFC numbers from the text
+ *
+ * @param {string} text Text to extract RFC numbers from
+ * @param {RegExp} regex Regular expression to extract RFC numbers
+ * @returns {Array<string>} Extracted RFC numbers
+ */
+function extractRfcNumbers (text, regex) {
+  const matches = {
+    rfcWithPrefix: [],
+    plainNumbers: []
+  }
+
+  let match
+  while ((match = regex.exec(text)) !== null) {
+    const rfcList = match[0]
+    if (rfcList) {
+      const numbers = rfcList
+        .match(/\b(RFC\s*[0-9]+|[0-9]+)\b/gi)
+        ?.map(num => num.trim()) || []
+      numbers.forEach(num => {
+        if (/^RFC\s*[0-9]+$/i.test(num)) {
+          matches.rfcWithPrefix.push(num)
+          matches.plainNumbers.push(num.replace(/^RFC\s*/i, ''))
+        } else {
+          matches.plainNumbers.push(num)
+        }
+      })
+    }
+  }
+
+  return matches
+}
diff --git a/tests/fixtures/txt-blocks/section-blocks.mjs b/tests/fixtures/txt-blocks/section-blocks.mjs
@@ -82,6 +82,23 @@ Updates: 6789, 7890, 8901, 9012 (if approved)
                  draft-ietf-idr-rt-derived-community-05
 `
 
+export const metaWithoutObsoleteAndUpdatesTXTBlock = `
+
+
+
+
+idr                                                            Z. Zhang
+Internet-Draft                                                  J. Haas
+Intended status: Standards Track                       Juniper Networks
+Expires: 8 September 2023                                      K. Patel
+                                                                Arrcus
+                                                        21 January 2025
+
+
+            Extended Communities Derived from Route Targets
+                 draft-ietf-idr-rt-derived-community-05
+`
+
 export const authorAddressTXTBlock = `
 Authors' Addresses