Function page_layout

src/__main__.py:581–803

(page, textout, GRID, fontsize, noformfeed, skip_empty, flags)

def page_layout(page, textout, GRID, fontsize, noformfeed, skip_empty, flags):
    eop = b"\n" if noformfeed else bytes([12])

    # --------------------------------------------------------------------
    def find_line_index(values: List[int], value: int) -> int:
        """Find the right row coordinate.

        Args:
            values: (list) y-coordinates of rows.
            value: (int) lookup for this value (y-origin of char).
        Returns:
            y-ccordinate of appropriate line for value.
        """
        i = bisect.bisect_right(values, value)
        if i:
            return values[i - 1]
        raise RuntimeError(f"Line for {value:g} not found in {values}")

    # --------------------------------------------------------------------
    def curate_rows(rows: Set[int], GRID) -> List:
        rows = list(rows)
        rows.sort()  # sort ascending
        nrows = [rows[0]]
        for h in rows[1:]:
            if h >= nrows[-1] + GRID:  # only keep significant differences
                nrows.append(h)
        return nrows  # curated list of line bottom coordinates

    def process_blocks(blocks: List[Dict], page: pymupdf.Page):
        rows = set()
        page_width = page.rect.width
        page_height = page.rect.height
        rowheight = page_height
        left = page_width
        right = 0
        chars = []
        for block in blocks:
            for line in block["lines"]:
                if line["dir"] != (1, 0):  # ignore non-horizontal text
                    continue
                x0, y0, x1, y1 = line["bbox"]
                if y1 < 0 or y0 > page.rect.height:  # ignore if outside CropBox
                    continue
                # upd row height
                height = y1 - y0

                if rowheight > height:
                    rowheight = height
                for span in line["spans"]:
                    if span["size"] <= fontsize:
                        continue
                    for c in span["chars"]:
                        x0, _, x1, _ = c["bbox"]
                        cwidth = x1 - x0
                        ox, oy = c["origin"]
                        oy = int(round(oy))
                        rows.add(oy)
                        ch = c["c"]