Skip to content

Move out receiving partitions in extractors out of loops #2529

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
norberttech merged 1 commit into from
Jul 12, 2026
Merged

Move out receiving partitions in extractors out of loops #2529

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion src/adapter/etl-adapter-csv/src/Flow/ETL/Adapter/CSV/CSVExtractor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,11 +73,11 @@ public function extract(FlowContext $context): Generator
$enclosure = $this->enclosure ?? $option->enclosure;
$escape = $this->escape ?? $option->escape;
$uri = $stream->path()->uri();
$partitions = $stream->path()->partitions();

$headers = [];
$headersCount = 0;
$streamUri = $shouldPutInputIntoRows ? $uri : null;
$partitions = $stream->path()->partitions();

$csvLineReader = new CSVLineReader($enclosure, $this->charactersReadInLine, $this->removeBOM);
$rowNormalizer = new CSVRowNormalizer($this->emptyToNull);
Expand Down
9 changes: 3 additions & 6 deletions src/adapter/etl-adapter-excel/src/Flow/ETL/Adapter/Excel/ExcelExtractor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,13 +74,10 @@ public function extract(FlowContext $context): Generator
$offset = $this->offset ?? 1;

foreach ($context->streams()->list($this->path, $this->filter()) as $stream) {
$partitions = $stream->path()->partitions();

foreach ($this->extractRows($stream, $headers, $offset) as $row) {
$signal = yield array_to_rows(
$row,
$context->entryFactory(),
$stream->path()->partitions(),
schema: $this->schema,
);
$signal = yield array_to_rows($row, $context->entryFactory(), $partitions, $this->schema);

$this->incrementReturnedRows();

Expand Down
8 changes: 2 additions & 6 deletions src/adapter/etl-adapter-json/src/Flow/ETL/Adapter/JSON/JSONMachine/JsonExtractor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@ public function extract(FlowContext $context): Generator

foreach ($context->streams()->list($this->path, $this->filter()) as $stream) {
$uri = $stream->path()->uri();
$partitions = $stream->path()->partitions();

/**
* @var array<string, mixed> $rowData
Expand All @@ -66,12 +67,7 @@ public function extract(FlowContext $context): Generator
continue;
}

$signal = yield array_to_rows(
[$row],
$context->entryFactory(),
$stream->path()->partitions(),
$this->schema,
);
$signal = yield array_to_rows([$row], $context->entryFactory(), $partitions, $this->schema);

$this->incrementReturnedRows();

Expand Down
8 changes: 2 additions & 6 deletions src/adapter/etl-adapter-json/src/Flow/ETL/Adapter/JSON/JSONMachine/JsonLinesExtractor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@ public function extract(FlowContext $context): Generator

foreach ($context->streams()->list($this->path, $this->filter()) as $stream) {
$uri = $stream->path()->uri();
$partitions = $stream->path()->partitions();

foreach ($stream->readLines() as $jsonLine) {
/**
Expand All @@ -81,12 +82,7 @@ public function extract(FlowContext $context): Generator
continue;
}

$signal = yield array_to_rows(
[$row],
$context->entryFactory(),
$stream->path()->partitions(),
$this->schema,
);
$signal = yield array_to_rows([$row], $context->entryFactory(), $partitions, $this->schema);

$this->incrementReturnedRows();

Expand Down
14 changes: 8 additions & 6 deletions src/adapter/etl-adapter-parquet/src/Flow/ETL/Adapter/Parquet/ParquetExtractor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,12 +69,6 @@ public function extract(FlowContext $context): Generator

foreach ($this->readers($context) as $fileData) {
$fileRows = $fileData['file']->metadata()->rowsNumber();
$flowSchema = $this->schemaConverter->toFlow($fileData['file']->schema());
$uri = $fileData['stream']->path()->uri();

if (count($this->columns)) {
$flowSchema = $flowSchema->keep(...$this->columns);
}

if ($fileOffset > $fileRows) {
$fileData['stream']->close();
Expand All @@ -83,6 +77,14 @@ public function extract(FlowContext $context): Generator
continue;
}

$flowSchema = $this->schemaConverter->toFlow($fileData['file']->schema());

if (count($this->columns)) {
$flowSchema = $flowSchema->keep(...$this->columns);
}

$uri = $fileData['stream']->path()->uri();

foreach ($fileData['file']->values($this->columns, $this->limit(), $fileOffset) as $row) {
$entries = [];

Expand Down
3 changes: 2 additions & 1 deletion src/adapter/etl-adapter-text/src/Flow/ETL/Adapter/Text/TextExtractor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@ public function extract(FlowContext $context): Generator

foreach ($context->streams()->list($this->path, $this->filter()) as $stream) {
$uri = $stream->path()->uri();
$partitions = $stream->path()->partitions();

foreach ($stream->readLines() as $rowData) {
if ($shouldPutInputIntoRows) {
Expand All @@ -46,7 +47,7 @@ public function extract(FlowContext $context): Generator
$row = [['text' => rtrim($rowData)]];
}

$signal = yield array_to_rows($row, $context->entryFactory(), $stream->path()->partitions());
$signal = yield array_to_rows($row, $context->entryFactory(), $partitions);

$this->incrementReturnedRows();

Expand Down
8 changes: 2 additions & 6 deletions src/adapter/etl-adapter-xml/src/Flow/ETL/Adapter/XML/XMLParserExtractor.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,6 +114,7 @@ public function extract(FlowContext $context): Generator

foreach ($context->streams()->list($this->path, $this->filter()) as $stream) {
$uri = $stream->path()->uri();
$partitions = $stream->path()->partitions();

foreach ($stream->iterate($this->bufferSize) as $chunk) {
if (!xml_parse($this->parser(), $chunk)) {
Expand All @@ -130,12 +131,7 @@ public function extract(FlowContext $context): Generator
$rowData['_input_file_uri'] = $uri;
}

$signal = yield array_to_rows(
$rowData,
$context->entryFactory(),
$stream->path()->partitions(),
$this->schema,
);
$signal = yield array_to_rows($rowData, $context->entryFactory(), $partitions, $this->schema);

$this->incrementReturnedRows();

Expand Down
Loading