printf: this commit adds support for https://github.com/tursodatabase/limbo/issues/885 tracking printf functionality

this commit introduces basic support for printf functionality and doesn't include advanced modifiers like width etc.

COMPAT.md

@@ -227,7 +227,7 @@ Feature support of [sqlite expr syntax](https://www.sqlite.org/lang_expr.html).
 | min(X,Y,...)                 | Yes     |                                                      |
 | nullif(X,Y)                  | Yes     |                                                      |
 | octet_length(X)              | Yes     |                                                      |
-| printf(FORMAT,...)           | No      |                                                      |
+| printf(FORMAT,...)           | Yes     | Still need support additional modifiers              |
 | quote(X)                     | Yes     |                                                      |
 | random()                     | Yes     |                                                      |
 | randomblob(N)                | Yes     |                                                      |

core/error.rs

@@ -39,6 +39,10 @@ pub enum LimboError {
     InvalidTime(String),
     #[error("Modifier parsing error: {0}")]
     InvalidModifier(String),
+    #[error("Invalid argument supplied: {0}")]
+    InvalidArgument(String),
+    #[error("Invalid formatter supplied: {0}")]
+    InvalidFormatter(String),
     #[error("Runtime error: {0}")]
     Constraint(String),
     #[error("Extension error: {0}")]

core/function.rs

@@ -221,6 +221,7 @@ pub enum ScalarFunc {
     #[cfg(not(target_family = "wasm"))]
     LoadExtension,
     StrfTime,
+    Printf,
 }
 
 impl Display for ScalarFunc {
@@ -274,6 +275,7 @@ impl Display for ScalarFunc {
             #[cfg(not(target_family = "wasm"))]
             Self::LoadExtension => "load_extension".to_string(),
             Self::StrfTime => "strftime".to_string(),
+            Self::Printf => "printf".to_string(),
         };
         write!(f, "{}", str)
     }
@@ -572,6 +574,7 @@ impl Func {
             #[cfg(not(target_family = "wasm"))]
             "load_extension" => Ok(Self::Scalar(ScalarFunc::LoadExtension)),
             "strftime" => Ok(Self::Scalar(ScalarFunc::StrfTime)),
+            "printf" => Ok(Self::Scalar(ScalarFunc::Printf)),
             _ => crate::bail_parse_error!("no such function: {}", name),
         }
     }

core/translate/expr.rs

@@ -1752,6 +1752,14 @@ pub fn translate_expr(
                             });
                             Ok(target_register)
                         }
+                        ScalarFunc::Printf => translate_function(
+                            program,
+                            args.as_deref().unwrap_or(&[]),
+                            referenced_tables,
+                            resolver,
+                            target_register,
+                            func_ctx,
+                        ),
                     }
                 }
                 Func::Math(math_func) => match math_func.arity() {

core/vdbe/mod.rs

@@ -22,6 +22,7 @@ mod datetime;
 pub mod explain;
 pub mod insn;
 pub mod likeop;
+mod printf;
 pub mod sorter;
 mod strftime;
 
@@ -57,6 +58,7 @@ use insn::{
     exec_subtract,
 };
 use likeop::{construct_like_escape_arg, exec_glob, exec_like_with_escape};
+use printf::exec_printf;
 use rand::distributions::{Distribution, Uniform};
 use rand::{thread_rng, Rng};
 use regex::{Regex, RegexBuilder};
@@ -2108,6 +2110,12 @@ impl Program {
                                 );
                                 state.registers[*dest] = result;
                             }
+                            ScalarFunc::Printf => {
+                                let result = exec_printf(
+                                    &state.registers[*start_reg..*start_reg + arg_count],
+                                )?;
+                                state.registers[*dest] = result;
+                            }
                         },
                         crate::function::Func::External(f) => match f.func {
                             ExtFunc::Scalar(f) => {

core/vdbe/printf.rs

@@ -0,0 +1,265 @@
+use std::rc::Rc;
+
+use crate::types::OwnedValue;
+use crate::LimboError;
+
+#[inline(always)]
+pub fn exec_printf(values: &[OwnedValue]) -> crate::Result<OwnedValue> {
+    if values.is_empty() {
+        return Ok(OwnedValue::Null);
+    }
+    let format_str = match &values[0] {
+        OwnedValue::Text(t) => &t.value,
+        _ => return Ok(OwnedValue::Null),
+    };
+
+    let mut result = String::new();
+    let mut args_index = 1;
+    let mut chars = format_str.chars().peekable();
+
+    while let Some(c) = chars.next() {
+        if c != '%' {
+            result.push(c);
+            continue;
+        }
+
+        match chars.next() {
+            Some('%') => {
+                result.push('%');
+                continue;
+            }
+            Some('d') => {
+                if args_index >= values.len() {
+                    return Err(LimboError::InvalidArgument("not enough arguments".into()));
+                }
+                match &values[args_index] {
+                    OwnedValue::Integer(i) => result.push_str(&i.to_string()),
+                    OwnedValue::Float(f) => result.push_str(&f.to_string()),
+                    _ => result.push_str("0".into()),
+                }
+                args_index += 1;
+            }
+            Some('s') => {
+                if args_index >= values.len() {
+                    return Err(LimboError::InvalidArgument("not enough arguments".into()));
+                }
+                match &values[args_index] {
+                    OwnedValue::Text(t) => result.push_str(&t.value),
+                    OwnedValue::Null => result.push_str("(null)"),
+                    v => result.push_str(&v.to_string()),
+                }
+                args_index += 1;
+            }
+            Some('f') => {
+                if args_index >= values.len() {
+                    return Err(LimboError::InvalidArgument("not enough arguments".into()));
+                }
+                match &values[args_index] {
+                    OwnedValue::Float(f) => result.push_str(&f.to_string()),
+                    OwnedValue::Integer(i) => result.push_str(&(*i as f64).to_string()),
+                    _ => result.push_str("0.0".into()),
+                }
+                args_index += 1;
+            }
+            None => {
+                return Err(LimboError::InvalidArgument(
+                    "incomplete format specifier".into(),
+                ))
+            }
+            _ => {
+                return Err(LimboError::InvalidFormatter(
+                    "this formatter is not supported".into(),
+                ));
+            }
+        }
+    }
+    Ok(OwnedValue::build_text(Rc::new(result)))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::rc::Rc;
+
+    fn text(value: &str) -> OwnedValue {
+        OwnedValue::build_text(Rc::new(value.to_string()))
+    }
+
+    fn integer(value: i64) -> OwnedValue {
+        OwnedValue::Integer(value)
+    }
+
+    fn float(value: f64) -> OwnedValue {
+        OwnedValue::Float(value)
+    }
+
+    #[test]
+    fn test_printf_no_args() {
+        assert_eq!(exec_printf(&[]).unwrap(), OwnedValue::Null);
+    }
+
+    #[test]
+    fn test_printf_basic_string() {
+        assert_eq!(
+            exec_printf(&[text("Hello World")]).unwrap(),
+            text("Hello World")
+        );
+    }
+
+    #[test]
+    fn test_printf_string_formatting() {
+        let test_cases = vec![
+            // Simple string substitution
+            (
+                vec![text("Hello, %s!"), text("World")],
+                text("Hello, World!"),
+            ),
+            // Multiple string substitutions
+            (
+                vec![text("%s %s!"), text("Hello"), text("World")],
+                text("Hello World!"),
+            ),
+            // String with null value
+            (
+                vec![text("Hello, %s!"), OwnedValue::Null],
+                text("Hello, (null)!"),
+            ),
+            // String with number conversion
+            (vec![text("Value: %s"), integer(42)], text("Value: 42")),
+            // Escaping percent sign
+            (vec![text("100%% complete")], text("100% complete")),
+        ];
+        for (input, output) in test_cases {
+            assert_eq!(exec_printf(&input).unwrap(), output);
+        }
+    }
+
+    #[test]
+    fn test_printf_integer_formatting() {
+        let test_cases = vec![
+            // Basic integer formatting
+            (vec![text("Number: %d"), integer(42)], text("Number: 42")),
+            // Negative integer
+            (vec![text("Number: %d"), integer(-42)], text("Number: -42")),
+            // Multiple integers
+            (
+                vec![text("%d + %d = %d"), integer(2), integer(3), integer(5)],
+                text("2 + 3 = 5"),
+            ),
+            // Non-numeric value defaults to 0
+            (
+                vec![text("Number: %d"), text("not a number")],
+                text("Number: 0"),
+            ),
+        ];
+        for (input, output) in test_cases {
+            assert_eq!(exec_printf(&input).unwrap(), output)
+        }
+    }
+
+    #[test]
+    fn test_printf_float_formatting() {
+        let test_cases = vec![
+            // Basic float formatting
+            (vec![text("Number: %f"), float(42.5)], text("Number: 42.5")),
+            // Negative float
+            (
+                vec![text("Number: %f"), float(-42.5)],
+                text("Number: -42.5"),
+            ),
+            // Integer as float
+            (vec![text("Number: %f"), integer(42)], text("Number: 42")),
+            // Multiple floats
+            (
+                vec![text("%f + %f = %f"), float(2.5), float(3.5), float(6.0)],
+                text("2.5 + 3.5 = 6"),
+            ),
+            // Non-numeric value defaults to 0.0
+            (
+                vec![text("Number: %f"), text("not a number")],
+                text("Number: 0.0"),
+            ),
+        ];
+
+        for (input, expected) in test_cases {
+            assert_eq!(exec_printf(&input).unwrap(), expected);
+        }
+    }
+
+    #[test]
+    fn test_printf_mixed_formatting() {
+        let test_cases = vec![
+            // Mix of string and integer
+            (
+                vec![text("%s: %d"), text("Count"), integer(42)],
+                text("Count: 42"),
+            ),
+            // Mix of all types
+            (
+                vec![
+                    text("%s: %d (%f%%)"),
+                    text("Progress"),
+                    integer(75),
+                    float(75.5),
+                ],
+                text("Progress: 75 (75.5%)"),
+            ),
+            // Complex format
+            (
+                vec![
+                    text("Name: %s, ID: %d, Score: %f"),
+                    text("John"),
+                    integer(123),
+                    float(95.5),
+                ],
+                text("Name: John, ID: 123, Score: 95.5"),
+            ),
+        ];
+
+        for (input, expected) in test_cases {
+            assert_eq!(exec_printf(&input).unwrap(), expected);
+        }
+    }
+
+    #[test]
+    fn test_printf_error_cases() {
+        let error_cases = vec![
+            // Not enough arguments
+            vec![text("%d %d"), integer(42)],
+            // Invalid format string
+            vec![text("%z"), integer(42)],
+            // Incomplete format specifier
+            vec![text("incomplete %")],
+        ];
+
+        for case in error_cases {
+            assert!(exec_printf(&case).is_err());
+        }
+    }
+
+    #[test]
+    fn test_printf_edge_cases() {
+        let test_cases = vec![
+            // Empty format string
+            (vec![text("")], text("")),
+            // Only percent signs
+            (vec![text("%%%%")], text("%%")),
+            // String with no format specifiers
+            (vec![text("No substitutions")], text("No substitutions")),
+            // Multiple consecutive format specifiers
+            (
+                vec![text("%d%d%d"), integer(1), integer(2), integer(3)],
+                text("123"),
+            ),
+            // Format string with special characters
+            (
+                vec![text("Special chars: %s"), text("\n\t\r")],
+                text("Special chars: \n\t\r"),
+            ),
+        ];
+
+        for (input, expected) in test_cases {
+            assert_eq!(exec_printf(&input).unwrap(), expected);
+        }
+    }
+}

testing/all.test

@@ -23,3 +23,4 @@ source $testdir/compare.test
 source $testdir/changes.test
 source $testdir/total-changes.test
 source $testdir/offset.test
+source $testdir/scalar-functions-printf.test

testing/scalar-functions-printf.test

@@ -0,0 +1,22 @@
+#!/usr/bin/env tclsh
+
+set testdir [file dirname $argv0]
+source $testdir/tester.tcl
+
+# Basic string formatting
+do_execsql_test printf-basic-string {
+  SELECT printf('Hello World!');
+} {{Hello World!}}
+
+do_execsql_test printf-string-replacement {
+  SELECT printf('Hello, %s', 'Alice');
+} {{Hello, Alice}}
+
+do_execsql_test printf-numeric-replacement {
+  SELECT printf('My number is: %d', 42);
+} {{My number is: 42}}
+
+# Multiple consecutive format specifiers
+do_execsql_test printf-consecutive-formats {
+  SELECT printf('%d%s%f', 1, 'test', 2.5);
+} {{1test2.500000}}