Merge pull request #3843 from ClickHouse/fix_aspell

Fix aspell

Author: Blargian

scripts/aspell-dict-file.txt

@@ -1054,4 +1054,4 @@ allowlist
 --docs/integrations/data-ingestion/azure-data-factory/overview.md--
 microsoft
 --docs/integrations/data-ingestion/azure-data-factory/index.md--
-microsoft
+microsoft

scripts/aspell-ignore/en/aspell-dict.txt

@@ -3517,4 +3517,5 @@ minSimpleState
 maxSimpleState
 TimescaleDB
 columnstore
-
+TiDB
+resync

scripts/check-doc-aspell

@@ -67,7 +67,32 @@ get_ignore_words_for_file() {
 # Use this to filter out lines we don't wanna consider in spell-check - slugs, imports, and img src JSX elements
 preprocess_file() {
     local file=$1
-    sed -E 's/\{#[^}]*\}//g' "$file" | grep -Ev '^(slug:|import [[:alnum:]_, {}*]+ from .+;?|<img src=\{[^}]+\})'
+
+    # Remove YAML frontmatter (everything between the first --- and second --- lines)
+    # Then apply other existing filters
+    awk '
+    BEGIN {
+        in_frontmatter = 0
+        frontmatter_ended = 0
+    }
+    # If first line is ---, we are starting frontmatter
+    /^---$/ && NR == 1 {
+        in_frontmatter = 1
+        next
+    }
+    # If we encounter --- while in frontmatter, end it
+    /^---$/ && in_frontmatter {
+        in_frontmatter = 0
+        frontmatter_ended = 1
+        next
+    }
+    # Print lines only if not in frontmatter
+    !in_frontmatter { print }
+    ' "$file" \
+        | sed -E 's/\{#[^}]*\}//g' \
+        | sed -E 's/<[A-Za-z0-9_]+svg[^>]*\/?>//g' \
+        | sed -E 's/<Image[^>]*\/?>//g' \
+        | grep -Ev '(^[[:space:]]*(slug:|<img src=\{[^}]+\})|^import .* from .*)'
 }
 # List of files to ignore
 IGNORE_LIST=(