docling 2.25.2__py3-none-any.whl → 2.27.0__py3-none-any.whl

docling/backend/docx/latex/omml.py

@@ -0,0 +1,453 @@
+"""
+Office Math Markup Language (OMML)
+
+Adapted from https://github.com/xiilei/dwml/blob/master/dwml/omml.py
+On 23/01/2025
+"""
+
+import lxml.etree as ET
+from pylatexenc.latexencode import UnicodeToLatexEncoder
+
+from docling.backend.docx.latex.latex_dict import (
+    ALN,
+    ARR,
+    BACKSLASH,
+    BLANK,
+    BRK,
+    CHARS,
+    CHR,
+    CHR_BO,
+    CHR_DEFAULT,
+    D_DEFAULT,
+    F_DEFAULT,
+    FUNC,
+    FUNC_PLACE,
+    LIM_FUNC,
+    LIM_TO,
+    LIM_UPP,
+    POS,
+    POS_DEFAULT,
+    RAD,
+    RAD_DEFAULT,
+    SUB,
+    SUP,
+    D,
+    F,
+    M,
+    T,
+)
+
+OMML_NS = "{http://schemas.openxmlformats.org/officeDocument/2006/math}"
+
+
+def load(stream):
+    tree = ET.parse(stream)
+    for omath in tree.findall(OMML_NS + "oMath"):
+        yield oMath2Latex(omath)
+
+
+def load_string(string):
+    root = ET.fromstring(string)
+    for omath in root.findall(OMML_NS + "oMath"):
+        yield oMath2Latex(omath)
+
+
+def escape_latex(strs):
+    last = None
+    new_chr = []
+    strs = strs.replace(r"\\", "\\")
+    for c in strs:
+        if (c in CHARS) and (last != BACKSLASH):
+            new_chr.append(BACKSLASH + c)
+        else:
+            new_chr.append(c)
+        last = c
+    return BLANK.join(new_chr)
+
+
+def get_val(key, default=None, store=CHR):
+    if key is not None:
+        return key if not store else store.get(key, key)
+    else:
+        return default
+
+
+class Tag2Method(object):
+
+    def call_method(self, elm, stag=None):
+        getmethod = self.tag2meth.get
+        if stag is None:
+            stag = elm.tag.replace(OMML_NS, "")
+        method = getmethod(stag)
+        if method:
+            return method(self, elm)
+        else:
+            return None
+
+    def process_children_list(self, elm, include=None):
+        """
+        process children of the elm,return iterable
+        """
+        for _e in list(elm):
+            if OMML_NS not in _e.tag:
+                continue
+            stag = _e.tag.replace(OMML_NS, "")
+            if include and (stag not in include):
+                continue
+            t = self.call_method(_e, stag=stag)
+            if t is None:
+                t = self.process_unknow(_e, stag)
+                if t is None:
+                    continue
+            yield (stag, t, _e)
+
+    def process_children_dict(self, elm, include=None):
+        """
+        process children of the elm,return dict
+        """
+        latex_chars = dict()
+        for stag, t, e in self.process_children_list(elm, include):
+            latex_chars[stag] = t
+        return latex_chars
+
+    def process_children(self, elm, include=None):
+        """
+        process children of the elm,return string
+        """
+        return BLANK.join(
+            (
+                t if not isinstance(t, Tag2Method) else str(t)
+                for stag, t, e in self.process_children_list(elm, include)
+            )
+        )
+
+    def process_unknow(self, elm, stag):
+        return None
+
+
+class Pr(Tag2Method):
+
+    text = ""
+
+    __val_tags = ("chr", "pos", "begChr", "endChr", "type")
+
+    __innerdict = None  # can't use the __dict__
+
+    """ common properties of element"""
+
+    def __init__(self, elm):
+        self.__innerdict = {}
+        self.text = self.process_children(elm)
+
+    def __str__(self):
+        return self.text
+
+    def __unicode__(self):
+        return self.__str__(self)
+
+    def __getattr__(self, name):
+        return self.__innerdict.get(name, None)
+
+    def do_brk(self, elm):
+        self.__innerdict["brk"] = BRK
+        return BRK
+
+    def do_common(self, elm):
+        stag = elm.tag.replace(OMML_NS, "")
+        if stag in self.__val_tags:
+            t = elm.get("{0}val".format(OMML_NS))
+            self.__innerdict[stag] = t
+        return None
+
+    tag2meth = {
+        "brk": do_brk,
+        "chr": do_common,
+        "pos": do_common,
+        "begChr": do_common,
+        "endChr": do_common,
+        "type": do_common,
+    }
+
+
+class oMath2Latex(Tag2Method):
+    """
+    Convert oMath element of omml to latex
+    """
+
+    _t_dict = T
+
+    __direct_tags = ("box", "sSub", "sSup", "sSubSup", "num", "den", "deg", "e")
+    u = UnicodeToLatexEncoder(
+        replacement_latex_protection="braces-all",
+        unknown_char_policy="keep",
+        unknown_char_warning=False,
+    )
+
+    def __init__(self, element):
+        self._latex = self.process_children(element)
+
+    def __str__(self):
+        return self.latex.replace("  ", " ")
+
+    def __unicode__(self):
+        return self.__str__(self)
+
+    def process_unknow(self, elm, stag):
+        if stag in self.__direct_tags:
+            return self.process_children(elm)
+        elif stag[-2:] == "Pr":
+            return Pr(elm)
+        else:
+            return None
+
+    @property
+    def latex(self):
+        return self._latex
+
+    def do_acc(self, elm):
+        """
+        the accent function
+        """
+        c_dict = self.process_children_dict(elm)
+        latex_s = get_val(
+            c_dict["accPr"].chr, default=CHR_DEFAULT.get("ACC_VAL"), store=CHR
+        )
+        return latex_s.format(c_dict["e"])
+
+    def do_bar(self, elm):
+        """
+        the bar function
+        """
+        c_dict = self.process_children_dict(elm)
+        pr = c_dict["barPr"]
+        latex_s = get_val(pr.pos, default=POS_DEFAULT.get("BAR_VAL"), store=POS)
+        return pr.text + latex_s.format(c_dict["e"])
+
+    def do_d(self, elm):
+        """
+        the delimiter object
+        """
+        c_dict = self.process_children_dict(elm)
+        pr = c_dict["dPr"]
+        null = D_DEFAULT.get("null")
+
+        s_val = get_val(pr.begChr, default=D_DEFAULT.get("left"), store=T)
+        e_val = get_val(pr.endChr, default=D_DEFAULT.get("right"), store=T)
+        delim = pr.text + D.format(
+            left=null if not s_val else escape_latex(s_val),
+            text=c_dict["e"],
+            right=null if not e_val else escape_latex(e_val),
+        )
+        return delim
+
+    def do_spre(self, elm):
+        """
+        the Pre-Sub-Superscript object -- Not support yet
+        """
+        pass
+
+    def do_sub(self, elm):
+        text = self.process_children(elm)
+        return SUB.format(text)
+
+    def do_sup(self, elm):
+        text = self.process_children(elm)
+        return SUP.format(text)
+
+    def do_f(self, elm):
+        """
+        the fraction object
+        """
+        c_dict = self.process_children_dict(elm)
+        pr = c_dict["fPr"]
+        latex_s = get_val(pr.type, default=F_DEFAULT, store=F)
+        return pr.text + latex_s.format(num=c_dict.get("num"), den=c_dict.get("den"))
+
+    def do_func(self, elm):
+        """
+        the Function-Apply object (Examples:sin cos)
+        """
+        c_dict = self.process_children_dict(elm)
+        func_name = c_dict.get("fName")
+        return func_name.replace(FUNC_PLACE, c_dict.get("e"))
+
+    def do_fname(self, elm):
+        """
+        the func name
+        """
+        latex_chars = []
+        for stag, t, e in self.process_children_list(elm):
+            if stag == "r":
+                if FUNC.get(t):
+                    latex_chars.append(FUNC[t])
+                else:
+                    raise NotSupport("Not support func %s" % t)
+            else:
+                latex_chars.append(t)
+        t = BLANK.join(latex_chars)
+        return t if FUNC_PLACE in t else t + FUNC_PLACE  # do_func will replace this
+
+    def do_groupchr(self, elm):
+        """
+        the Group-Character object
+        """
+        c_dict = self.process_children_dict(elm)
+        pr = c_dict["groupChrPr"]
+        latex_s = get_val(pr.chr)
+        return pr.text + latex_s.format(c_dict["e"])
+
+    def do_rad(self, elm):
+        """
+        the radical object
+        """
+        c_dict = self.process_children_dict(elm)
+        text = c_dict.get("e")
+        deg_text = c_dict.get("deg")
+        if deg_text:
+            return RAD.format(deg=deg_text, text=text)
+        else:
+            return RAD_DEFAULT.format(text=text)
+
+    def do_eqarr(self, elm):
+        """
+        the Array object
+        """
+        return ARR.format(
+            text=BRK.join(
+                [t for stag, t, e in self.process_children_list(elm, include=("e",))]
+            )
+        )
+
+    def do_limlow(self, elm):
+        """
+        the Lower-Limit object
+        """
+        t_dict = self.process_children_dict(elm, include=("e", "lim"))
+        latex_s = LIM_FUNC.get(t_dict["e"])
+        if not latex_s:
+            raise NotSupport("Not support lim %s" % t_dict["e"])
+        else:
+            return latex_s.format(lim=t_dict.get("lim"))
+
+    def do_limupp(self, elm):
+        """
+        the Upper-Limit object
+        """
+        t_dict = self.process_children_dict(elm, include=("e", "lim"))
+        return LIM_UPP.format(lim=t_dict.get("lim"), text=t_dict.get("e"))
+
+    def do_lim(self, elm):
+        """
+        the lower limit of the limLow object and the upper limit of the limUpp function
+        """
+        return self.process_children(elm).replace(LIM_TO[0], LIM_TO[1])
+
+    def do_m(self, elm):
+        """
+        the Matrix object
+        """
+        rows = []
+        for stag, t, e in self.process_children_list(elm):
+            if stag == "mPr":
+                pass
+            elif stag == "mr":
+                rows.append(t)
+        return M.format(text=BRK.join(rows))
+
+    def do_mr(self, elm):
+        """
+        a single row of the matrix m
+        """
+        return ALN.join(
+            [t for stag, t, e in self.process_children_list(elm, include=("e",))]
+        )
+
+    def do_nary(self, elm):
+        """
+        the n-ary object
+        """
+        res = []
+        bo = ""
+        for stag, t, e in self.process_children_list(elm):
+            if stag == "naryPr":
+                bo = get_val(t.chr, store=CHR_BO)
+            else:
+                res.append(t)
+        return bo + BLANK.join(res)
+
+    def process_unicode(self, s):
+        # s = s if isinstance(s,unicode) else unicode(s,'utf-8')
+        # print(s, self._t_dict.get(s, s), unicode_to_latex(s))
+        # _str.append( self._t_dict.get(s, s) )
+
+        out_latex_str = self.u.unicode_to_latex(s)
+
+        # print(s, out_latex_str)
+
+        if (
+            s.startswith("{") is False
+            and out_latex_str.startswith("{")
+            and s.endswith("}") is False
+            and out_latex_str.endswith("}")
+        ):
+            out_latex_str = f" {out_latex_str[1:-1]} "
+
+        # print(s, out_latex_str)
+
+        if "ensuremath" in out_latex_str:
+            out_latex_str = out_latex_str.replace("\\ensuremath{", " ")
+            out_latex_str = out_latex_str.replace("}", " ")
+
+        # print(s, out_latex_str)
+
+        if out_latex_str.strip().startswith("\\text"):
+            out_latex_str = f" \\text{{{out_latex_str}}} "
+
+        # print(s, out_latex_str)
+
+        return out_latex_str
+
+    def do_r(self, elm):
+        """
+        Get text from 'r' element,And try convert them to latex symbols
+        @todo text style support , (sty)
+        @todo \text (latex pure text support)
+        """
+        _str = []
+        _base_str = []
+        for s in elm.findtext("./{0}t".format(OMML_NS)):
+            out_latex_str = self.process_unicode(s)
+            _str.append(out_latex_str)
+            _base_str.append(s)
+
+        proc_str = escape_latex(BLANK.join(_str))
+        base_proc_str = BLANK.join(_base_str)
+
+        if "{" not in base_proc_str and "\\{" in proc_str:
+            proc_str = proc_str.replace("\\{", "{")
+
+        if "}" not in base_proc_str and "\\}" in proc_str:
+            proc_str = proc_str.replace("\\}", "}")
+
+        return proc_str
+
+    tag2meth = {
+        "acc": do_acc,
+        "r": do_r,
+        "bar": do_bar,
+        "sub": do_sub,
+        "sup": do_sup,
+        "f": do_f,
+        "func": do_func,
+        "fName": do_fname,
+        "groupChr": do_groupchr,
+        "d": do_d,
+        "rad": do_rad,
+        "eqArr": do_eqarr,
+        "limLow": do_limlow,
+        "limUpp": do_limupp,
+        "lim": do_lim,
+        "m": do_m,
+        "mr": do_mr,
+        "nary": do_nary,
+    }

docling/backend/html_backend.py

@@ -134,7 +134,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                     self.analyze_tag(cast(Tag, element), doc)
                 except Exception as exc_child:
                     _log.error(
-                        f"Error processing child from tag{tag.name}: {exc_child}"
+                        f"Error processing child from tag {tag.name}: {repr(exc_child)}"
                     )
                     raise exc_child
             elif isinstance(element, NavigableString) and not isinstance(
@@ -347,11 +347,11 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                     content_layer=self.content_layer,
                 )
                 self.level += 1
-
-            self.walk(element, doc)
-
-            self.parents[self.level + 1] = None
-            self.level -= 1
+                self.walk(element, doc)
+                self.parents[self.level + 1] = None
+                self.level -= 1
+            else:
+                self.walk(element, doc)
 
         elif element.text.strip():
             text = element.text.strip()
@@ -457,7 +457,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                     end_row_offset_idx=row_idx + row_span,
                     start_col_offset_idx=col_idx,
                     end_col_offset_idx=col_idx + col_span,
-                    col_header=col_header,
+                    column_header=col_header,
                     row_header=((not col_header) and html_cell.name == "th"),
                 )
                 data.table_cells.append(table_cell)

docling/backend/md_backend.py

@@ -136,7 +136,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                         end_row_offset_idx=trow_ind + row_span,
                         start_col_offset_idx=tcol_ind,
                         end_col_offset_idx=tcol_ind + col_span,
-                        col_header=False,
+                        column_header=trow_ind == 0,
                         row_header=False,
                     )
                     tcells.append(icell)

docling/backend/msexcel_backend.py

@@ -164,7 +164,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
                     end_row_offset_idx=excel_cell.row + excel_cell.row_span,
                     start_col_offset_idx=excel_cell.col,
                     end_col_offset_idx=excel_cell.col + excel_cell.col_span,
-                    col_header=False,
+                    column_header=excel_cell.row == 0,
                     row_header=False,
                 )
                 table_data.table_cells.append(cell)
@@ -173,7 +173,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
 
         return doc
 
-    def _find_data_tables(self, sheet: Worksheet):
+    def _find_data_tables(self, sheet: Worksheet) -> List[ExcelTable]:
         """
         Find all compact rectangular data tables in a sheet.
         """
@@ -340,47 +340,4 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
             except:
                 _log.error("could not extract the image from excel sheets")
 
-        """
-        for idx, chart in enumerate(sheet._charts):  # type: ignore
-            try:
-                chart_path = f"chart_{idx + 1}.png"
-                _log.info(
-                    f"Chart found, but dynamic rendering is required for: {chart_path}"
-                )
-
-                _log.info(f"Chart {idx + 1}:")
-                
-                # Chart type
-                # _log.info(f"Type: {type(chart).__name__}")
-                print(f"Type: {type(chart).__name__}")
-
-                # Extract series data
-                for series_idx, series in enumerate(chart.series):
-                    #_log.info(f"Series {series_idx + 1}:")
-                    print(f"Series {series_idx + 1} type: {type(series).__name__}")
-                    #print(f"x-values: {series.xVal}")
-                    #print(f"y-values: {series.yVal}")
-
-                    print(f"xval type: {type(series.xVal).__name__}")
-                    
-                    xvals = []
-                    for _ in series.xVal.numLit.pt:
-                        print(f"xval type: {type(_).__name__}")
-                        if hasattr(_, 'v'):
-                            xvals.append(_.v)
-
-                    print(f"x-values: {xvals}")
-                            
-                    yvals = []
-                    for _ in series.yVal:
-                        if hasattr(_, 'v'):
-                            yvals.append(_.v)
-                            
-                    print(f"y-values: {yvals}")                    
-                    
-            except Exception as exc:
-                print(exc)
-                continue
-        """
-
         return doc

docling/backend/mspowerpoint_backend.py

@@ -346,7 +346,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
                         end_row_offset_idx=row_idx + row_span,
                         start_col_offset_idx=col_idx,
                         end_col_offset_idx=col_idx + col_span,
-                        col_header=False,
+                        column_header=row_idx == 0,
                         row_header=False,
                     )
                     if len(cell.text.strip()) > 0:

docling/backend/msword_backend.py

@@ -26,6 +26,7 @@ from PIL import Image, UnidentifiedImageError
 from typing_extensions import override
 
 from docling.backend.abstract_backend import DeclarativeDocumentBackend
+from docling.backend.docx.latex.omml import oMath2Latex
 from docling.datamodel.base_models import InputFormat
 from docling.datamodel.document import InputDocument
 
@@ -260,6 +261,25 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         else:
             return label, None
 
+    def handle_equations_in_text(self, element, text):
+        only_texts = []
+        only_equations = []
+        texts_and_equations = []
+        for subt in element.iter():
+            tag_name = etree.QName(subt).localname
+            if tag_name == "t" and "math" not in subt.tag:
+                only_texts.append(subt.text)
+                texts_and_equations.append(subt.text)
+            elif "oMath" in subt.tag and "oMathPara" not in subt.tag:
+                latex_equation = str(oMath2Latex(subt))
+                only_equations.append(latex_equation)
+                texts_and_equations.append(latex_equation)
+
+        if "".join(only_texts) != text:
+            return text
+
+        return "".join(texts_and_equations), only_equations
+
     def handle_text_elements(
         self,
         element: BaseOxmlElement,
@@ -268,9 +288,12 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
     ) -> None:
         paragraph = Paragraph(element, docx_obj)
 
-        if paragraph.text is None:
+        raw_text = paragraph.text
+        text, equations = self.handle_equations_in_text(element=element, text=raw_text)
+
+        if text is None:
             return
-        text = paragraph.text.strip()
+        text = text.strip()
 
         # Common styles for bullet and numbered lists.
         # "List Bullet", "List Number", "List Paragraph"
@@ -323,6 +346,45 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         elif "Heading" in p_style_id:
             self.add_header(doc, p_level, text)
 
+        elif len(equations) > 0:
+            if (raw_text is None or len(raw_text) == 0) and len(text) > 0:
+                # Standalone equation
+                level = self.get_level()
+                doc.add_text(
+                    label=DocItemLabel.FORMULA,
+                    parent=self.parents[level - 1],
+                    text=text,
+                )
+            else:
+                # Inline equation
+                level = self.get_level()
+                inline_equation = doc.add_group(
+                    label=GroupLabel.INLINE, parent=self.parents[level - 1]
+                )
+                text_tmp = text
+                for eq in equations:
+                    if len(text_tmp) == 0:
+                        break
+                    pre_eq_text = text_tmp.split(eq, maxsplit=1)[0]
+                    text_tmp = text_tmp.split(eq, maxsplit=1)[1]
+                    if len(pre_eq_text) > 0:
+                        doc.add_text(
+                            label=DocItemLabel.PARAGRAPH,
+                            parent=inline_equation,
+                            text=pre_eq_text,
+                        )
+                    doc.add_text(
+                        label=DocItemLabel.FORMULA,
+                        parent=inline_equation,
+                        text=eq,
+                    )
+                if len(text_tmp) > 0:
+                    doc.add_text(
+                        label=DocItemLabel.PARAGRAPH,
+                        parent=inline_equation,
+                        text=text_tmp,
+                    )
+
         elif p_style_id in [
             "Paragraph",
             "Normal",
@@ -539,7 +601,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                     end_row_offset_idx=row.grid_cols_before + spanned_idx,
                     start_col_offset_idx=col_idx,
                     end_col_offset_idx=col_idx + cell.grid_span,
-                    col_header=False,
+                    column_header=row.grid_cols_before + row_idx == 0,
                     row_header=False,
                 )
                 data.table_cells.append(table_cell)

docling/backend/pdf_backend.py

@@ -4,10 +4,11 @@ from pathlib import Path
 from typing import Iterable, Optional, Set, Union
 
 from docling_core.types.doc import BoundingBox, Size
+from docling_core.types.doc.page import SegmentedPdfPage, TextCell
 from PIL import Image
 
 from docling.backend.abstract_backend import PaginatedDocumentBackend
-from docling.datamodel.base_models import Cell, InputFormat
+from docling.datamodel.base_models import InputFormat
 from docling.datamodel.document import InputDocument
 
 
@@ -17,7 +18,11 @@ class PdfPageBackend(ABC):
         pass
 
     @abstractmethod
-    def get_text_cells(self) -> Iterable[Cell]:
+    def get_segmented_page(self) -> Optional[SegmentedPdfPage]:
+        pass
+
+    @abstractmethod
+    def get_text_cells(self) -> Iterable[TextCell]:
         pass
 
     @abstractmethod