dumpling-cli 0.4.2__tar.gz → 0.4.3__tar.gz

{dumpling_cli-0.4.2 → dumpling_cli-0.4.3}/CHANGELOG.md

@@ -7,6 +7,12 @@ and this project follows [Semantic Versioning](https://semver.org/spec/v2.0.0.ht
 
 ## [Unreleased]
 
+## [0.4.3] - 2026-05-03
+
+### Fixed
+
+- **COPY row integrity after anonymization**: Control characters in anonymized COPY text fields are escaped so tab/newline/etc. cannot break column alignment or row boundaries ([#53](https://github.com/ababic/dumpling/pull/53)).
+
 ## [0.4.2] - 2026-05-03
 
 ### Fixed
@@ -68,6 +74,7 @@ and this project follows [Semantic Versioning](https://semver.org/spec/v2.0.0.ht
 - Configurable output scan severities and per-category thresholds via `[output_scan]`.
 - JSON report section for output scan findings including category, count, threshold, severity, and sample locations.
 
+[0.4.3]: https://github.com/ababic/dumpling/compare/v0.4.2...v0.4.3
 [0.4.2]: https://github.com/ababic/dumpling/compare/v0.4.1...v0.4.2
 [0.4.1]: https://github.com/ababic/dumpling/compare/v0.4.0...v0.4.1
 [0.4.0]: https://github.com/ababic/dumpling/compare/v0.3.0...v0.4.0

{dumpling_cli-0.4.2 → dumpling_cli-0.4.3}/Cargo.lock

@@ -262,7 +262,7 @@ dependencies = [
 
 [[package]]
 name = "dumpling"
-version = "0.4.2"
+version = "0.4.3"
 dependencies = [
  "anyhow",
  "chrono",

{dumpling_cli-0.4.2 → dumpling_cli-0.4.3}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "dumpling"
-version = "0.4.2"
+version = "0.4.3"
 edition = "2021"
 readme = "README.md"
 

{dumpling_cli-0.4.2 → dumpling_cli-0.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dumpling-cli
-Version: 0.4.2
+Version: 0.4.3
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers

{dumpling_cli-0.4.2 → dumpling_cli-0.4.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "dumpling-cli"
-version = "0.4.2"
+version = "0.4.3"
 description = "Static anonymizer for plain SQL dumps (PostgreSQL, SQLite, SQL Server)."
 readme = "README.md"
 requires-python = ">=3.8"

{dumpling_cli-0.4.2 → dumpling_cli-0.4.3}/src/sql.rs

@@ -299,7 +299,8 @@ impl SqlStreamProcessor {
                                     if repl.is_null {
                                         new_fields.push(r"\N".to_string());
                                     } else {
-                                        new_fields.push(repl.value);
+                                        new_fields
+                                            .push(escape_postgres_copy_text_field(&repl.value));
                                     }
                                 }
                                 Err(e) => return Err(e),
@@ -1181,6 +1182,32 @@ impl Cell {
     }
 }
 
+/// Escapes a field value for PostgreSQL `COPY ... FROM stdin` **text** format so the output
+/// line still has one physical TAB-separated field per logical column. Without this, a
+/// replacement containing a literal TAB or newline would split the row on restore and surface
+/// as PostgreSQL errors like `missing data for column "..."`.
+fn escape_postgres_copy_text_field(s: &str) -> String {
+    let mut out = String::with_capacity(s.len());
+    for c in s.chars() {
+        match c {
+            '\\' => out.push_str("\\\\"),
+            '\t' => out.push_str("\\t"),
+            '\n' => out.push_str("\\n"),
+            '\r' => out.push_str("\\r"),
+            '\u{0008}' => out.push_str("\\b"),
+            '\u{000c}' => out.push_str("\\f"),
+            '\u{000b}' => out.push_str("\\v"),
+            '\0' => out.push_str("\\0"),
+            c if (c as u32) < 0x20 => {
+                use std::fmt::Write;
+                let _ = write!(out, "\\x{:02x}", c as u32);
+            }
+            c => out.push(c),
+        }
+    }
+    out
+}
+
 fn render_cell(repl: &Replacement, original: &Cell) -> String {
     let trailing = original.trailing_expr.as_deref().unwrap_or("");
     if repl.is_null {
@@ -2119,6 +2146,15 @@ INSERT INTO public.users (id, email) VALUES
         );
     }
 
+    #[test]
+    fn escape_postgres_copy_text_field_escapes_control_chars() {
+        assert_eq!(
+            escape_postgres_copy_text_field("a\tb\nc\\"),
+            "a\\tb\\nc\\\\"
+        );
+        assert_eq!(escape_postgres_copy_text_field("\0\u{01}"), "\\0\\x01");
+    }
+
     #[test]
     fn domain_mapping_null_and_non_null_cross_table_consistency() {
         // When the same domain spans two tables, NULL stays NULL in both, and