Skip to content

Percent array heredoc continuation #3778

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
kddnewton merged 2 commits into from
Dec 3, 2025
Merged

Percent array heredoc continuation #3778

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
2116770
Correctly handle line continuations in %w/i% interrupted by heredocs
Earlopain Dec 3, 2025
1bc8ec5
Fix wrong error message for lower percent i arrays
Earlopain Dec 3, 2025
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
56 changes: 33 additions & 23 deletions snapshots/spanning_heredoc.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,19 +192,24 @@
│ │ │ └── unescaped: "i\n"
│ │ └── @ ArrayNode (location: (28,9)-(31,2))
│ │ ├── flags: ∅
│ │ ├── elements: (length: 2)
│ │ │ ├── @ StringNode (location: (28,12)-(28,14))
│ │ │ │ ├── flags: ∅
│ │ │ │ ├── opening_loc: ∅
│ │ │ │ ├── content_loc: (28,12)-(28,14) = "j\\"
│ │ │ │ ├── closing_loc: ∅
│ │ │ │ └── unescaped: "j\n"
│ │ │ └── @ StringNode (location: (31,0)-(31,1))
│ │ ├── elements: (length: 1)
│ │ │ └── @ InterpolatedStringNode (location: (28,12)-(31,1))
│ │ │ ├── flags: ∅
│ │ │ ├── opening_loc: ∅
│ │ │ ├── content_loc: (31,0)-(31,1) = "j"
│ │ │ ├── closing_loc: ∅
│ │ │ └── unescaped: "j"
│ │ │ ├── parts: (length: 2)
│ │ │ │ ├── @ StringNode (location: (28,12)-(28,14))
│ │ │ │ │ ├── flags: static_literal, frozen
│ │ │ │ │ ├── opening_loc: ∅
│ │ │ │ │ ├── content_loc: (28,12)-(28,14) = "j\\"
│ │ │ │ │ ├── closing_loc: ∅
│ │ │ │ │ └── unescaped: "j\n"
│ │ │ │ └── @ StringNode (location: (31,0)-(31,1))
│ │ │ │ ├── flags: static_literal, frozen
│ │ │ │ ├── opening_loc: ∅
│ │ │ │ ├── content_loc: (31,0)-(31,1) = "j"
│ │ │ │ ├── closing_loc: ∅
│ │ │ │ └── unescaped: "j"
│ │ │ └── closing_loc: ∅
│ │ ├── opening_loc: (28,9)-(28,12) = "%w["
│ │ └── closing_loc: (31,1)-(31,2) = "]"
│ ├── closing_loc: ∅
Expand Down Expand Up @@ -271,19 +276,24 @@
│ │ │ └── unescaped: "m\n"
│ │ └── @ ArrayNode (location: (41,9)-(44,2))
│ │ ├── flags: static_literal
│ │ ├── elements: (length: 2)
│ │ │ ├── @ SymbolNode (location: (41,12)-(41,14))
│ │ │ │ ├── flags: static_literal, forced_us_ascii_encoding
│ │ │ │ ├── opening_loc: ∅
│ │ │ │ ├── value_loc: (41,12)-(41,14) = "n\\"
│ │ │ │ ├── closing_loc: ∅
│ │ │ │ └── unescaped: "n\n"
│ │ │ └── @ SymbolNode (location: (44,0)-(44,1))
│ │ │ ├── flags: static_literal, forced_us_ascii_encoding
│ │ ├── elements: (length: 1)
│ │ │ └── @ InterpolatedSymbolNode (location: (41,12)-(41,14))
│ │ │ ├── flags: static_literal
│ │ │ ├── opening_loc: ∅
│ │ │ ├── value_loc: (44,0)-(44,1) = "n"
│ │ │ ├── closing_loc: ∅
│ │ │ └── unescaped: "n"
│ │ │ ├── parts: (length: 2)
│ │ │ │ ├── @ StringNode (location: (41,12)-(41,14))
│ │ │ │ │ ├── flags: static_literal, frozen
│ │ │ │ │ ├── opening_loc: ∅
│ │ │ │ │ ├── content_loc: (41,12)-(41,14) = "n\\"
│ │ │ │ │ ├── closing_loc: ∅
│ │ │ │ │ └── unescaped: "n\n"
│ │ │ │ └── @ StringNode (location: (41,12)-(41,14))
│ │ │ │ ├── flags: static_literal, frozen
│ │ │ │ ├── opening_loc: ∅
│ │ │ │ ├── content_loc: (41,12)-(41,14) = "n\\"
│ │ │ │ ├── closing_loc: ∅
│ │ │ │ └── unescaped: "n"
│ │ │ └── closing_loc: ∅
│ │ ├── opening_loc: (41,9)-(41,12) = "%i["
│ │ └── closing_loc: (44,1)-(44,2) = "]"
│ ├── closing_loc: ∅
Expand Down
71 changes: 62 additions & 9 deletions src/prism.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19299,18 +19299,52 @@ parse_expression_prefix(pm_parser_t *parser, pm_binding_power_t binding_power, b
parser_lex(parser);
pm_token_t opening = parser->previous;
pm_array_node_t *array = pm_array_node_create(parser, &opening);
pm_node_t *current = NULL;

while (!match2(parser, PM_TOKEN_STRING_END, PM_TOKEN_EOF)) {
accept1(parser, PM_TOKEN_WORDS_SEP);
if (match1(parser, PM_TOKEN_STRING_END)) break;

if (match1(parser, PM_TOKEN_STRING_CONTENT)) {
// Interpolation is not possible but nested heredocs can still lead to
// consecutive (disjoint) string tokens when the final newline is escaped.
while (match1(parser, PM_TOKEN_STRING_CONTENT)) {
pm_token_t opening = not_provided(parser);
pm_token_t closing = not_provided(parser);
pm_array_node_elements_append(array, UP(pm_symbol_node_create_current_string(parser, &opening, &parser->current, &closing)));

// Record the string node, moving to interpolation if needed.
if (current == NULL) {
current = UP(pm_symbol_node_create_current_string(parser, &opening, &parser->current, &closing));
parser_lex(parser);
} else if (PM_NODE_TYPE_P(current, PM_INTERPOLATED_SYMBOL_NODE)) {
pm_node_t *string = UP(pm_string_node_create_current_string(parser, &opening, &parser->current, &closing));
parser_lex(parser);
pm_interpolated_symbol_node_append((pm_interpolated_symbol_node_t *) current, string);
} else if (PM_NODE_TYPE_P(current, PM_SYMBOL_NODE)) {
pm_symbol_node_t *cast = (pm_symbol_node_t *) current;
pm_token_t bounds = not_provided(parser);

pm_token_t content = { .type = PM_TOKEN_STRING_CONTENT, .start = cast->value_loc.start, .end = cast->value_loc.end };
pm_node_t *first_string = UP(pm_string_node_create_unescaped(parser, &bounds, &content, &bounds, &cast->unescaped));
pm_node_t *second_string = UP(pm_string_node_create_current_string(parser, &opening, &parser->previous, &closing));
parser_lex(parser);

pm_interpolated_symbol_node_t *interpolated = pm_interpolated_symbol_node_create(parser, &opening, NULL, &closing);
pm_interpolated_symbol_node_append(interpolated, first_string);
pm_interpolated_symbol_node_append(interpolated, second_string);

xfree(current);
current = UP(interpolated);
} else {
assert(false && "unreachable");
}
}

expect1(parser, PM_TOKEN_STRING_CONTENT, PM_ERR_LIST_I_LOWER_ELEMENT);
if (current) {
pm_array_node_elements_append(array, current);
current = NULL;
} else {
expect1(parser, PM_TOKEN_STRING_CONTENT, PM_ERR_LIST_I_LOWER_ELEMENT);
}
}

pm_token_t closing = parser->current;
Expand Down Expand Up @@ -19489,23 +19523,42 @@ parse_expression_prefix(pm_parser_t *parser, pm_binding_power_t binding_power, b
parser_lex(parser);
pm_token_t opening = parser->previous;
pm_array_node_t *array = pm_array_node_create(parser, &opening);

// skip all leading whitespaces
accept1(parser, PM_TOKEN_WORDS_SEP);
Copy link
Collaborator Author

@Earlopain Earlopain Dec 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This was not needed, the loop already consumsed the separator. Removed because it was already not present in %i handling

pm_node_t *current = NULL;

while (!match2(parser, PM_TOKEN_STRING_END, PM_TOKEN_EOF)) {
accept1(parser, PM_TOKEN_WORDS_SEP);
if (match1(parser, PM_TOKEN_STRING_END)) break;

if (match1(parser, PM_TOKEN_STRING_CONTENT)) {
// Interpolation is not possible but nested heredocs can still lead to
// consecutive (disjoint) string tokens when the final newline is escaped.
while (match1(parser, PM_TOKEN_STRING_CONTENT)) {
pm_token_t opening = not_provided(parser);
pm_token_t closing = not_provided(parser);

pm_node_t *string = UP(pm_string_node_create_current_string(parser, &opening, &parser->current, &closing));
pm_array_node_elements_append(array, string);

// Record the string node, moving to interpolation if needed.
if (current == NULL) {
current = string;
} else if (PM_NODE_TYPE_P(current, PM_INTERPOLATED_STRING_NODE)) {
pm_interpolated_string_node_append((pm_interpolated_string_node_t *) current, string);
} else if (PM_NODE_TYPE_P(current, PM_STRING_NODE)) {
pm_interpolated_string_node_t *interpolated = pm_interpolated_string_node_create(parser, &opening, NULL, &closing);
pm_interpolated_string_node_append(interpolated, current);
pm_interpolated_string_node_append(interpolated, string);
current = UP(interpolated);
} else {
assert(false && "unreachable");
}
parser_lex(parser);
}

expect1(parser, PM_TOKEN_STRING_CONTENT, PM_ERR_LIST_W_LOWER_ELEMENT);
if (current) {
pm_array_node_elements_append(array, current);
current = NULL;
} else {
expect1(parser, PM_TOKEN_STRING_CONTENT, PM_ERR_LIST_W_LOWER_ELEMENT);
}
}

pm_token_t closing = parser->current;
Expand Down