fix(clippy): resolve all lint errors for Rust 1.94 (round 2)

Author: claude

core/src/composite_document_parser/extract/structured.rs

@@ -84,7 +84,7 @@ pub(super) fn parse_ipynb(path: &Path) -> Result<ParsedDocument> {
             .with_ordinal(0)
             .with_attribute("record_type", "notebook-metadata");
             if !payload.is_empty() {
-                if let Some(serialized) = serde_json::to_string(&payload).ok() {
+                if let Ok(serialized) = serde_json::to_string(&payload) {
                     block = block.with_structured_payload(serialized);
                 }
             }
@@ -145,7 +145,7 @@ pub(super) fn parse_ipynb(path: &Path) -> Result<ParsedDocument> {
                 .with_source("cells")
                 .with_ordinal(idx + 1)
                 .with_attribute("cell_type", cell_type);
-            if let Some(serialized) = serde_json::to_string(&payload).ok() {
+            if let Ok(serialized) = serde_json::to_string(&payload) {
                 block = block.with_structured_payload(serialized);
             }
             doc.push(block);

core/src/composite_document_parser/extract/text.rs

@@ -164,7 +164,7 @@ fn process_table_row_markers(text: &str, default_kind: DocumentBlockKind) -> Vec
             table_rows.clear();
             // Also flush any pending text
             if !current_text.trim().is_empty() {
-                result.extend(chunk_to_blocks(&current_text.trim(), default_kind.clone()));
+                result.extend(chunk_to_blocks(current_text.trim(), default_kind.clone()));
                 current_text.clear();
             }
             // Process this non-table line
@@ -190,7 +190,7 @@ fn process_table_row_markers(text: &str, default_kind: DocumentBlockKind) -> Vec
 
     // Flush remaining text
     if !current_text.trim().is_empty() {
-        result.extend(chunk_to_blocks(&current_text.trim(), default_kind));
+        result.extend(chunk_to_blocks(current_text.trim(), default_kind));
     }
 
     result

core/src/composite_document_parser/format/container.rs

@@ -189,15 +189,15 @@ pub(super) fn parse_7z(path: &Path) -> Result<ParsedDocument> {
         );
     };
 
-    let entries = list_7z_entries(&binary, path)?;
+    let entries = list_7z_entries(binary, path)?;
     let entry_count = entries.len();
     let mut extracted = Vec::new();
     for name in entries {
         let lower = name.to_ascii_lowercase();
         if !is_archive_entry_candidate(&lower) {
             continue;
         }
-        let bytes = extract_7z_entry(&binary, path, &name)?;
+        let bytes = extract_7z_entry(binary, path, &name)?;
         extracted.push((name, bytes));
     }
 
@@ -599,15 +599,15 @@ fn parse_7z_bytes(name: &str, bytes: Vec<u8>, depth: usize) -> Result<ParsedDocu
         anyhow::bail!("no 7z/7zz/7za binary found on PATH");
     };
 
-    let entries = list_7z_entries(&binary, &path)?;
+    let entries = list_7z_entries(binary, &path)?;
     let entry_count = entries.len();
     let mut extracted = Vec::new();
     for entry_name in entries {
         let lower = entry_name.to_ascii_lowercase();
         if !is_archive_entry_candidate(&lower) {
             continue;
         }
-        let bytes = extract_7z_entry(&binary, &path, &entry_name)?;
+        let bytes = extract_7z_entry(binary, &path, &entry_name)?;
         extracted.push((entry_name, bytes));
     }
 
@@ -745,7 +745,7 @@ fn decode_text_bytes(bytes: &[u8]) -> Result<String> {
         return Ok(text.to_string());
     }
 
-    if bytes.len() >= 2 && bytes.len() % 2 == 0 {
+    if bytes.len() >= 2 && bytes.len().is_multiple_of(2) {
         let utf16: Vec<u16> = bytes
             .chunks_exact(2)
             .map(|chunk| u16::from_le_bytes([chunk[0], chunk[1]]))

core/src/composite_document_parser/format/office.rs

@@ -857,7 +857,7 @@ fn normalize_legacy_text(text: &str, kind: LegacyOfficeKind) -> String {
 }
 
 fn decode_utf16le_text(bytes: &[u8]) -> Option<String> {
-    if bytes.len() < 4 || bytes.len() % 2 != 0 {
+    if bytes.len() < 4 || !bytes.len().is_multiple_of(2) {
         return None;
     }
 
@@ -1472,7 +1472,7 @@ pub(super) fn infer_xlsb_row_major_rows(values: &[String]) -> Option<Vec<Vec<Str
     let mut best: Option<(usize, Vec<Vec<String>>)> = None;
 
     for column_count in 2..=max_columns {
-        if values.len() % column_count != 0 {
+        if !values.len().is_multiple_of(column_count) {
             continue;
         }
 
@@ -1503,7 +1503,7 @@ pub(super) fn infer_xlsb_column_major_rows(values: &[String]) -> Option<Vec<Vec<
     let mut best: Option<(usize, Vec<Vec<String>>)> = None;
 
     for column_count in 2..=max_columns {
-        if values.len() % column_count != 0 {
+        if !values.len().is_multiple_of(column_count) {
             continue;
         }
         let rows_per_column = values.len() / column_count;

core/src/composite_document_parser/format/structured.rs

@@ -19,7 +19,7 @@ pub(super) fn parse_ics_string(
     normalize_text: fn(&str) -> String,
     tagged_fields_to_text: fn(&std::collections::BTreeMap<String, String>, &[&str]) -> String,
 ) -> Result<ParsedDocument> {
-    let lines = unfold_structured_text_lines(&raw);
+    let lines = unfold_structured_text_lines(raw);
     let mut doc = ParsedDocument::new();
     doc.title = super::file_title(path);
 
@@ -118,7 +118,7 @@ pub(super) fn parse_vcf_string(
     normalize_text: fn(&str) -> String,
     tagged_fields_to_text: fn(&std::collections::BTreeMap<String, String>, &[&str]) -> String,
 ) -> Result<ParsedDocument> {
-    let lines = unfold_structured_text_lines(&raw);
+    let lines = unfold_structured_text_lines(raw);
     let mut doc = ParsedDocument::new();
     doc.title = super::file_title(path);
 

core/src/composite_document_parser/mail/email.rs

@@ -110,7 +110,7 @@ pub(super) fn push_mail_blocks(
             .with_source("message")
             .with_ordinal(ordinal)
             .with_attribute("record_type", "email-headers");
-            if let Some(serialized) = serde_json::to_string(&payload).ok() {
+            if let Ok(serialized) = serde_json::to_string(&payload) {
                 block = block.with_structured_payload(serialized);
             }
             doc.push(block);

core/src/composite_document_parser/mail/msg.rs

@@ -127,7 +127,7 @@ pub(super) fn parse_msg(path: &Path, normalize_text: fn(&str) -> String) -> Resu
         .with_source("msg")
         .with_ordinal(1)
         .with_attribute("record_type", "email-headers");
-        if let Some(serialized) = serde_json::to_string(&payload).ok() {
+        if let Ok(serialized) = serde_json::to_string(&payload) {
             block = block.with_structured_payload(serialized);
         }
         doc.push(block);
@@ -161,7 +161,7 @@ pub(super) fn parse_msg(path: &Path, normalize_text: fn(&str) -> String) -> Resu
         .with_ordinal(3)
         .with_attribute("record_type", "attachments")
         .with_attribute("attachment_count", attachments.len().to_string());
-        if let Some(payload) = serde_json::to_string(&attachments).ok() {
+        if let Ok(payload) = serde_json::to_string(&attachments) {
             block = block.with_structured_payload(payload);
         }
         doc.push(block);
@@ -551,8 +551,7 @@ fn select_subject(strings: &[String]) -> Option<String> {
         .iter()
         .find(|text| {
             let len = text.chars().count();
-            len >= 4
-                && len <= 120
+            (4..=120).contains(&len)
                 && text
                     .chars()
                     .next()

core/src/composite_document_parser/normalize/paged.rs

@@ -317,12 +317,12 @@ pub(super) fn append_page_lines(page: &str, extra_lines: &[String]) -> String {
 pub(super) fn remove_first_n_non_empty_lines(page: &str, count: usize) -> String {
     let mut removed = 0usize;
     page.lines()
-        .filter_map(|line| {
+        .filter(|line| {
             if removed < count && !line.trim().is_empty() {
                 removed += 1;
-                None
+                false
             } else {
-                Some(line)
+                true
             }
         })
         .collect::<Vec<_>>()

core/src/composite_document_parser/ocr/mod.rs

@@ -399,6 +399,7 @@ fn parse_pdf(path: &Path) -> Result<String> {
 #[derive(Debug, Clone)]
 struct PositionedTextItem {
     page: usize,
+    #[allow(dead_code)]
     y: f32,
     x: f32,
     text: String,

core/src/doc/mod.rs

@@ -11,7 +11,7 @@ pub(crate) mod registry;
 pub use model::{
     DocumentBlock, DocumentBlockKind, DocumentBlockLocation, DocumentConfidence,
     DocumentExtractionMetadata, DocumentMetadata, DocumentProvenance, ExtractedDocument,
-    ParsedDocument, StructuredElement, StructuredElementKind,
+    ParsedDocument,
 };
 pub use parser::DocumentParser;
 pub use registry::DocumentParserRegistry;