Function process_blocks

src/__main__.py:609–659

(blocks: List[Dict], page: pymupdf.Page)

        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"]
                        if left > ox and ch != " ":
                            left = ox  # update left coordinate
                        if right < x1:
                            right = x1  # update right coordinate
                        # handle ligatures:
                        if cwidth == 0 and chars != []:  # potential ligature
                            old_ch, old_ox, old_oy, old_cwidth = chars[-1]
                            if old_oy == oy:  # ligature
                                if old_ch != chr(0xFB00):  # previous "ff" char lig?
                                    lig = joinligature(old_ch + ch)  # no
                                # convert to one of the 3-char ligatures:
                                elif ch == "i":
                                    lig = chr(0xFB03)  # "ffi"
                                elif ch == "l":
                                    lig = chr(0xFB04)  # "ffl"
                                else:  # something wrong, leave old char in place
                                    lig = old_ch
                                chars[-1] = (lig, old_ox, old_oy, old_cwidth)
                                continue
                        chars.append((ch, ox, oy, cwidth))  # all chars on page
        return chars, rows, left, right, rowheight

    def joinligature(lig: str) -> str:
        """Return ligature character for a given pair / triple of characters.