Function get_matching_regions

src/licensedcode/match.py:2325–2395

Return a list of token query position Spans, where each Span represents a region of related LicenseMatch contained that Span given a ``matches`` list of LicenseMatch. Matching regions are such that: - all matches in the regions are entirely contained in the region Span Tw

(
    matches,
    min_tokens_gap=10,
    min_lines_gap=3,
    trace=TRACE_REGIONS,
)

def get_matching_regions(
    matches,
    min_tokens_gap=10,
    min_lines_gap=3,
    trace=TRACE_REGIONS,
):
    """
    Return a list of token query position Spans, where each Span represents a
    region of related LicenseMatch contained that Span given a ``matches`` list
    of LicenseMatch.

    Matching regions are such that:

    - all matches in the regions are entirely contained in the region Span

    Two consecutive region Spans are such that:

    - there are no overlaping matches between them
    - there are at least ``min_tokens_gap`` unmatched tokens between them
    - OR there are at least ``min_lines_gap`` unmatched lines between them
    """
    regions = []

    prev_region = None
    prev_region_lines = None
    cur_region = None
    cur_region_lines = None

    for match in matches:
        if trace:
            logger_debug('Match:', match)
        if not prev_region:
            prev_region = match.qregion()
            prev_region_lines = match.qregion_lines()
        else:
            cur_region = match.qregion()
            cur_region_lines = match.qregion_lines()

            if trace:
                logger_debug(
                    '  prev_region:', prev_region,
                    'cur_region:', cur_region,
                    'prev_region.distance_to(cur_region):',
                    prev_region.distance_to(cur_region),
                )
                logger_debug(
                    '  prev_region_lines:', prev_region_lines,
                    'cur_region_lines:', cur_region_lines,
                    'prev_region_lines.distance_to(cur_region_lines):',
                    prev_region_lines.distance_to(cur_region_lines)
                )

            if (prev_region.distance_to(cur_region) > min_tokens_gap
                or prev_region_lines.distance_to(cur_region_lines) > min_lines_gap
            ):

                regions.append(prev_region)