feat: multiple-CSV import

This commit is contained in:
Edward Langley
2026-04-02 16:21:45 -07:00
parent be277f43c2
commit dd728ccac8
3 changed files with 108 additions and 27 deletions

1
.envrc
View File

@ -1 +1,2 @@
use flake use flake
unset TMPDIR

View File

@ -56,6 +56,28 @@ pub fn parse_csv(path: &Path) -> Result<Vec<Value>> {
Ok(records) Ok(records)
} }
/// Parse multiple CSV files and merge into a single JSON array.
/// Each record gets a "File" field set to the filename stem (e.g., "sales" from "sales.csv").
pub fn merge_csvs(paths: &[impl AsRef<Path>]) -> Result<Vec<Value>> {
let mut all_records = Vec::new();
for path in paths {
let path = path.as_ref();
let stem = path
.file_stem()
.and_then(|s| s.to_str())
.unwrap_or("unknown")
.to_string();
let records = parse_csv(path)?;
for mut record in records {
if let Value::Object(ref mut map) = record {
map.insert("File".to_string(), Value::String(stem.clone()));
}
all_records.push(record);
}
}
Ok(all_records)
}
fn parse_csv_field(field: &str) -> Value { fn parse_csv_field(field: &str) -> Value {
if field.is_empty() { if field.is_empty() {
return Value::Null; return Value::Null;
@ -158,6 +180,40 @@ mod tests {
assert_eq!(records[0]["Active"], Value::String("true".to_string())); assert_eq!(records[0]["Active"], Value::String("true".to_string()));
} }
#[test]
fn merge_csvs_adds_file_field_from_stem() {
let dir = tempdir().unwrap();
let sales = dir.path().join("sales.csv");
let expenses = dir.path().join("expenses.csv");
fs::write(&sales, "Region,Revenue\nEast,100\nWest,200").unwrap();
fs::write(&expenses, "Region,Revenue\nEast,50\nWest,75").unwrap();
let records = merge_csvs(&[sales, expenses]).unwrap();
assert_eq!(records.len(), 4);
assert_eq!(records[0]["File"], Value::String("sales".to_string()));
assert_eq!(records[1]["File"], Value::String("sales".to_string()));
assert_eq!(records[2]["File"], Value::String("expenses".to_string()));
assert_eq!(records[3]["File"], Value::String("expenses".to_string()));
// Original fields preserved
assert_eq!(records[0]["Region"], Value::String("East".to_string()));
assert_eq!(
records[2]["Revenue"],
Value::Number(serde_json::Number::from(50))
);
}
#[test]
fn merge_csvs_single_file_works() {
let dir = tempdir().unwrap();
let path = dir.path().join("data.csv");
fs::write(&path, "Name,Value\nA,1").unwrap();
let records = merge_csvs(&[path]).unwrap();
assert_eq!(records.len(), 1);
assert_eq!(records[0]["File"], Value::String("data".to_string()));
assert_eq!(records[0]["Name"], Value::String("A".to_string()));
}
#[test] #[test]
fn parse_checking_csv_format() { fn parse_checking_csv_format() {
// Simulates the format of /Users/edwlan/Downloads/Checking1.csv // Simulates the format of /Users/edwlan/Downloads/Checking1.csv

View File

@ -29,7 +29,7 @@ trait Runnable {
struct CmdLineArgs { struct CmdLineArgs {
file_path: Option<PathBuf>, file_path: Option<PathBuf>,
import_path: Option<PathBuf>, import_paths: Vec<PathBuf>,
} }
impl Runnable for CmdLineArgs { impl Runnable for CmdLineArgs {
@ -38,36 +38,55 @@ impl Runnable for CmdLineArgs {
let model = get_initial_model(&self.file_path)?; let model = get_initial_model(&self.file_path)?;
// Pre-TUI import: parse JSON or CSV and open wizard // Pre-TUI import: parse JSON or CSV and open wizard
let import_value = self.import_path.and_then(get_import_data); let import_value = if self.import_paths.is_empty() {
None
} else {
get_import_data(&self.import_paths)
};
run_tui(model, self.file_path, import_value) run_tui(model, self.file_path, import_value)
} }
} }
fn get_import_data(path: PathBuf) -> Option<Value> { fn get_import_data(paths: &[PathBuf]) -> Option<Value> {
match std::fs::read_to_string(&path) { let all_csv = paths.iter().all(|p| csv_path_p(p));
Err(e) => {
eprintln!("Cannot read '{}': {e}", path.display()); if paths.len() > 1 {
None if !all_csv {
eprintln!("Multi-file import only supports CSV files");
return None;
} }
Ok(content) => { match crate::import::csv_parser::merge_csvs(paths) {
if csv_path_p(&path) { Ok(records) => Some(Value::Array(records)),
// Parse CSV and wrap as JSON array Err(e) => {
match crate::import::csv_parser::parse_csv(&path) { eprintln!("CSV merge error: {e}");
Ok(records) => Some(serde_json::Value::Array(records)), None
Err(e) => { }
eprintln!("CSV parse error: {e}"); }
None } else {
let path = &paths[0];
match std::fs::read_to_string(path) {
Err(e) => {
eprintln!("Cannot read '{}': {e}", path.display());
None
}
Ok(content) => {
if csv_path_p(path) {
match crate::import::csv_parser::parse_csv(path) {
Ok(records) => Some(Value::Array(records)),
Err(e) => {
eprintln!("CSV parse error: {e}");
None
}
} }
} } else {
} else { match serde_json::from_str::<Value>(&content) {
// Parse JSON Err(e) => {
match serde_json::from_str::<serde_json::Value>(&content) { eprintln!("JSON parse error: {e}");
Err(e) => { None
eprintln!("JSON parse error: {e}"); }
None Ok(json) => Some(json),
} }
Ok(json) => Some(json),
} }
} }
} }
@ -127,7 +146,8 @@ impl Runnable for HelpArgs {
println!("improvise — multi-dimensional data modeling TUI\n"); println!("improvise — multi-dimensional data modeling TUI\n");
println!("USAGE:"); println!("USAGE:");
println!(" improvise [file.improv] Open or create a model"); println!(" improvise [file.improv] Open or create a model");
println!(" improvise --import data.json Import JSON (or CSV) then open TUI"); println!(" improvise --import data.json Import JSON or CSV then open TUI");
println!(" improvise --import a.csv b.csv Import multiple CSVs (filenames become a category)");
println!(" improvise --cmd '{{...}}' Run a JSON command (headless, repeatable)"); println!(" improvise --cmd '{{...}}' Run a JSON command (headless, repeatable)");
println!(" improvise --script cmds.jsonl Run commands from file (headless)"); println!(" improvise --script cmds.jsonl Run commands from file (headless)");
println!("\nTUI KEYS (vim-style):"); println!("\nTUI KEYS (vim-style):");
@ -154,7 +174,7 @@ fn parse_args(args: Vec<String>) -> Box<dyn Runnable> {
let mut file_path: Option<PathBuf> = None; let mut file_path: Option<PathBuf> = None;
let mut headless_cmds: Vec<String> = Vec::new(); let mut headless_cmds: Vec<String> = Vec::new();
let mut headless_script: Option<PathBuf> = None; let mut headless_script: Option<PathBuf> = None;
let mut import_path: Option<PathBuf> = None; let mut import_paths: Vec<PathBuf> = Vec::new();
let mut i = 1; let mut i = 1;
while i < args.len() { while i < args.len() {
@ -171,7 +191,11 @@ fn parse_args(args: Vec<String>) -> Box<dyn Runnable> {
} }
"--import" => { "--import" => {
i += 1; i += 1;
import_path = args.get(i).map(PathBuf::from); while i < args.len() && !args[i].starts_with('-') {
import_paths.push(PathBuf::from(&args[i]));
i += 1;
}
continue; // skip the i += 1 at the bottom
} }
"--help" | "-h" => { "--help" | "-h" => {
return Box::new(HelpArgs); return Box::new(HelpArgs);
@ -193,7 +217,7 @@ fn parse_args(args: Vec<String>) -> Box<dyn Runnable> {
} else { } else {
Box::new(CmdLineArgs { Box::new(CmdLineArgs {
file_path, file_path,
import_path, import_paths,
}) })
} }
} }