Skip to content

fix: make --xml-root and --xml-row work for XML input parsing #140

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vmvarela merged 2 commits into from
May 8, 2026
Merged

fix: make --xml-root and --xml-row work for XML input parsing #140

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
926d21e
fix: make --xml-root and --xml-row work for XML input parsing
vmvarela May 8, 2026
3dcb9b9
fix: address oracle code review findings for PR #140
vmvarela May 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
83 changes: 81 additions & 2 deletions build.zig
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1066,9 +1066,10 @@ pub fn build(b: *std.Build) void {
test_xml_validate.step.dependOn(b.getInstallStep());
test_step.dependOn(&test_xml_validate.step);

// Integration test 104: --xml-root and --xml-row customize element names
// Integration test 104: --xml-root and --xml-row customize element names for output
const test_xml_custom_elements = b.addSystemCommand(&.{
"bash", "-c",
// Output: custom element names appear in the XML
\\result=$(printf 'name,age\nAlice,30\n' \
\\ | ./zig-out/bin/sql-pipe -O xml --xml-root data --xml-row record 'SELECT * FROM t')
\\echo "$result" | grep -q '<data>' && echo "$result" | grep -q '<record>' && echo "$result" | grep -q '</data>'
Expand Down Expand Up @@ -1108,7 +1109,7 @@ pub fn build(b: *std.Build) void {
// Integration test 108: Root sin rows → error con "no row elements"
const test_xml_no_rows = b.addSystemCommand(&.{
"bash", "-c",
\\msg=$(printf '<root></root>' | ./zig-out/bin/sql-pipe -I xml 'SELECT 1' 2>&1; echo "EXIT:$?")
\\msg=$(printf '<results></results>' | ./zig-out/bin/sql-pipe -I xml 'SELECT 1' 2>&1; echo "EXIT:$?")
\\echo "$msg" | grep -q 'no row elements' && echo "$msg" | grep -qv 'EXIT:0'
});
test_xml_no_rows.step.dependOn(b.getInstallStep());
Expand Down Expand Up @@ -1162,6 +1163,84 @@ pub fn build(b: *std.Build) void {
test_xml_float_as_int.step.dependOn(b.getInstallStep());
test_step.dependOn(&test_xml_float_as_int.step);

// Integration test 114: --xml-root navigates nested XML for input (RSS-like structure)
const test_xml_nested_navigation = b.addSystemCommand(&.{
"bash", "-c",
// Feed with <feed><channel><item> structure; --xml-root channel --xml-row item
// selects only item elements from inside channel, skipping <title> etc.
\\doc='<feed><channel><title>My Feed</title><item><name>Alice</name><age>30</age></item><item><name>Bob</name><age>25</age></item></channel></feed>'
\\result=$(printf '%s' "$doc" \
\\ | ./zig-out/bin/sql-pipe -I xml --xml-root channel --xml-row item \
\\ 'SELECT name || ":" || age FROM t ORDER BY name')
\\[ "$result" = "$(printf 'Alice:30\nBob:25')" ]
});
test_xml_nested_navigation.step.dependOn(b.getInstallStep());
test_step.dependOn(&test_xml_nested_navigation.step);

// Integration test 115: --xml-root / --xml-row with --validate counts only matching rows
const test_xml_nested_validate = b.addSystemCommand(&.{
"bash", "-c",
\\doc='<feed><channel><title>T</title><item><val>1</val></item><item><val>2</val></item></channel></feed>'
\\result=$(printf '%s' "$doc" \
\\ | ./zig-out/bin/sql-pipe -I xml --xml-root channel --xml-row item --validate)
\\echo "$result" | grep -q 'OK: 2 rows'
});
test_xml_nested_validate.step.dependOn(b.getInstallStep());
test_step.dependOn(&test_xml_nested_validate.step);

// Integration test 116: --xml-root alone (no --xml-row) navigates to container
const test_xml_root_alone = b.addSystemCommand(&.{
"bash", "-c",
\\doc='<feed><data><row><name>Alice</name></row><row><name>Bob</name></row></data></feed>'
\\result=$(printf '%s' "$doc" \
\\ | ./zig-out/bin/sql-pipe -I xml --xml-root data 'SELECT name FROM t ORDER BY name')
\\[ "$result" = "$(printf 'Alice\nBob')" ]
});
test_xml_root_alone.step.dependOn(b.getInstallStep());
test_step.dependOn(&test_xml_root_alone.step);

// Integration test 117: --xml-row alone (no --xml-root) filters rows by tag
const test_xml_row_alone = b.addSystemCommand(&.{
"bash", "-c",
\\doc='<results><item><name>Alice</name></item><meta><x>1</x></meta><item><name>Bob</name></item></results>'
\\result=$(printf '%s' "$doc" \
\\ | ./zig-out/bin/sql-pipe -I xml --xml-row item 'SELECT name FROM t ORDER BY name')
\\[ "$result" = "$(printf 'Alice\nBob')" ]
});
test_xml_row_alone.step.dependOn(b.getInstallStep());
test_step.dependOn(&test_xml_row_alone.step);

// Integration test 118: --xml-row with no matching elements exits non-zero with clear message
const test_xml_row_no_match = b.addSystemCommand(&.{
"bash", "-c",
\\msg=$(printf '<results><row><name>Alice</name></row></results>' \
\\ | ./zig-out/bin/sql-pipe -I xml --xml-row wrong 'SELECT 1' 2>&1; echo "EXIT:$?")
\\echo "$msg" | grep -q "'wrong'" && echo "$msg" | grep -q 'check --xml-row' && echo "$msg" | grep -qv 'EXIT:0'
});
test_xml_row_no_match.step.dependOn(b.getInstallStep());
test_step.dependOn(&test_xml_row_no_match.step);

// Integration test 119: --columns with --xml-root and --xml-row
const test_xml_columns_with_flags = b.addSystemCommand(&.{
"bash", "-c",
\\doc='<feed><channel><item><name>Alice</name><age>30</age></item></channel></feed>'
\\result=$(printf '%s' "$doc" \
\\ | ./zig-out/bin/sql-pipe -I xml --xml-root channel --xml-row item --columns)
\\[ "$result" = "$(printf 'name\nage')" ]
});
test_xml_columns_with_flags.step.dependOn(b.getInstallStep());
test_step.dependOn(&test_xml_columns_with_flags.step);

// Integration test 120: --xml-root matching the actual document root (fast path)
const test_xml_root_fast_path = b.addSystemCommand(&.{
"bash", "-c",
\\result=$(printf '<results><row><name>Alice</name></row></results>' \
\\ | ./zig-out/bin/sql-pipe -I xml --xml-root results 'SELECT name FROM t')
\\[ "$result" = "Alice" ]
});
test_xml_root_fast_path.step.dependOn(b.getInstallStep());
test_step.dependOn(&test_xml_root_fast_path.step);

// Unit tests for the RFC 4180 CSV parser (src/csv.zig)
const unit_tests = b.addTest(.{
.root_module = b.createModule(.{
Expand Down
30 changes: 27 additions & 3 deletions src/main.zig
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,10 @@ const ParsedArgs = struct {
xml_root: []const u8,
/// Row element name for XML output (default: "row").
xml_row: []const u8,
/// Root element to navigate to for XML input; null = use actual document root.
xml_root_input: ?[]const u8,
/// Row tag filter for XML input; null = accept any direct child element as a row.
xml_row_input: ?[]const u8,
};

/// Arguments for `--columns` mode.
Expand All @@ -115,6 +119,10 @@ const ColumnsArgs = struct {
verbose: bool,
/// Input format (default: csv).
input_format: InputFormat,
/// Root element to navigate to for XML input; null = use actual document root.
xml_root_input: ?[]const u8,
/// Row tag filter for XML input; null = accept any direct child element as a row.
xml_row_input: ?[]const u8,
};

/// Arguments for `--validate` mode.
Expand All @@ -125,6 +133,10 @@ const ValidateArgs = struct {
type_inference: bool,
/// Input format (default: csv).
input_format: InputFormat,
/// Root element to navigate to for XML input; null = use actual document root.
xml_root_input: ?[]const u8,
/// Row tag filter for XML input; null = accept any direct child element as a row.
xml_row_input: ?[]const u8,
};

/// Arguments for `--sample` mode.
Expand Down Expand Up @@ -298,6 +310,8 @@ fn parseArgs(args: []const [:0]const u8) SqlPipeError!ArgsResult {
var output: ?[]const u8 = null;
var xml_root: []const u8 = "results";
var xml_row: []const u8 = "row";
var xml_root_input: ?[]const u8 = null;
var xml_row_input: ?[]const u8 = null;
var sample_mode = false;
var sample_n: usize = 10;

Expand Down Expand Up @@ -400,14 +414,18 @@ fn parseArgs(args: []const [:0]const u8) SqlPipeError!ArgsResult {
i += 1;
if (i >= args.len) return error.MissingXmlFlagValue;
xml_root = args[i];
xml_root_input = args[i];
} else if (std.mem.startsWith(u8, arg, "--xml-root=")) {
xml_root = arg["--xml-root=".len..];
xml_root_input = arg["--xml-root=".len..];
} else if (std.mem.eql(u8, arg, "--xml-row")) {
i += 1;
if (i >= args.len) return error.MissingXmlFlagValue;
xml_row = args[i];
xml_row_input = args[i];
} else if (std.mem.startsWith(u8, arg, "--xml-row=")) {
xml_row = arg["--xml-row=".len..];
xml_row_input = arg["--xml-row=".len..];
} else {
if (query == null) query = arg;
}
Expand Down Expand Up @@ -471,6 +489,8 @@ fn parseArgs(args: []const [:0]const u8) SqlPipeError!ArgsResult {
.delimiter = delimiter,
.verbose = verbose,
.input_format = input_format,
.xml_root_input = xml_root_input,
.xml_row_input = xml_row_input,
} };

// --validate mode: parse CSV and print summary
Expand All @@ -479,6 +499,8 @@ fn parseArgs(args: []const [:0]const u8) SqlPipeError!ArgsResult {
.delimiter = delimiter,
.type_inference = type_inference,
.input_format = input_format,
.xml_root_input = xml_root_input,
.xml_row_input = xml_row_input,
} };

// --sample mode: print schema + first n rows and exit
Expand All @@ -503,6 +525,8 @@ fn parseArgs(args: []const [:0]const u8) SqlPipeError!ArgsResult {
.output = output,
.xml_root = xml_root,
.xml_row = xml_row,
.xml_root_input = xml_root_input,
.xml_row_input = xml_row_input,
} };
}

Expand Down Expand Up @@ -1509,7 +1533,7 @@ fn runColumns(
var stdin_buf: [4096]u8 = undefined;
var stdin_file_reader = std.Io.File.reader(std.Io.File.stdin(), io, &stdin_buf);

const names = xml.getXmlColumnNames(allocator, &stdin_file_reader.interface, stderr_writer);
const names = xml.getXmlColumnNames(allocator, &stdin_file_reader.interface, args.xml_root_input, args.xml_row_input, stderr_writer);
defer {
for (names) |name| allocator.free(name);
allocator.free(names);
Expand Down Expand Up @@ -1799,7 +1823,7 @@ fn runValidate(
var stdin_buf: [4096]u8 = undefined;
var stdin_file_reader = std.Io.File.reader(std.Io.File.stdin(), io, &stdin_buf);

const summary = xml.summarizeXml(allocator, &stdin_file_reader.interface, stderr_writer);
const summary = xml.summarizeXml(allocator, &stdin_file_reader.interface, args.xml_root_input, args.xml_row_input, stderr_writer);
defer {
for (summary.col_names) |name| allocator.free(name);
allocator.free(summary.col_names);
Expand Down Expand Up @@ -2019,7 +2043,7 @@ fn run(
.xml => blk: {
var stdin_buf: [4096]u8 = undefined;
var stdin_reader = std.Io.File.reader(std.Io.File.stdin(), io, &stdin_buf);
break :blk xml.loadXmlInput(allocator, &stdin_reader.interface, db, parsed.max_rows, stderr_writer);
break :blk xml.loadXmlInput(allocator, &stdin_reader.interface, db, parsed.xml_root_input, parsed.xml_row_input, parsed.max_rows, stderr_writer);
},
};

Expand Down
Loading
Loading