khw"dZddlZddlmZddlmZddlmZddlm Z ddl m Z m Z m Z dd lmZed gd ZGd d e Zy)a(Extract fonts properties from PDF. Font properties like font name, size are covered in :py:class:`~pdf2docx.text.TextSpan`, but more generic properties are required further: * Font family name. The font name extracted and set in ``TextSpan`` might not valid when directly used in MS Word, e.g. "ArialMT" should be "Arial". So, we need to get font family name, which should be accepted by MS Word, based on the font file itself. * Font line height ratio. As line height = font_size * line_height_ratio, it's used to calculate relative line spacing. In general, 1.12 is an approximate value to this ratio, but it's in fact a font-related value, especially for CJK font. * So, extract font metrics, e.g. ascender and descender, with third party library ``fontTools`` in first priority. This can obtain an accurate line height ratio, but sometimes the embedded font data might crash. * Then, we have to use the default properties, i.e. ascender and descender, extracted by ``PyMuPDF`` directly, but this value isn't so accurate. N)BytesIO) namedtuple)TTFont)BaseCollection)CJK_CODEPAGE_BITSCJK_UNICODE_RANGE_BITSCJK_UNICODE_RANGES)decodeFont descriptorname line_heightceZdZdZdefdZedZedZ edefdZ ede fd Z ede fd Z ede fd Zy ) Fontsz$Extracted fonts properties from PDF. font_namec|j|}|D]}||jk(s|cS|D]}||jvs|cS|D]}|j|vs|cSy)z.Get matched font by font name, or return None.N)_to_descriptorr)selfrtargetfonts O/var/www/teggl/fontify/venv/lib/python3.12/site-packages/pdf2docx/font/Fonts.pygetz Fonts.get'sz$$Y/ 4Dt&t  4 6D(+ 6 6D&(+ 6ct}|D]+}|jD]}|j|d-g}|D]}|j|\}}} } |st |}|j |} |dvsJdt t| } |j| } |j| } |jt|j| | | ||S#t$rd} YCwxYw)zExtract fonts from PDF and get properties. * Only embedded fonts (v.s. the base 14 fonts) can be extracted. * The extracted fonts may be invalid due to reason from PDF file itself. r)zn/acffzbase font or not supported fontNr )set get_fontsadd extract_fontr _normalized_font_namerrget_font_family_nameget_line_height_factor Exceptionappendr r)clsfitz_docxrefspageffontsxrefbasenameext_bufferrttrs rextractz Fonts.extract:s 7D^^% 6uyy1 6 7 *D'/'<' Calibri.+-r)splitrs rr"zFonts._normalized_font_namecs'zz#r"((-a00rrcb|jddjddjS)zBRemove potential space, dash in font name, and turn to upper case. r7)replaceupperr9s rrzFonts._to_descriptoris+||C$,,S"5;;==rtt_fontcJdx}}d}d}|djD]u}d|jvr|jjd}n|jjd}|j|k(r|s|}n|j|k(r|s|}|sr|suntj |S)z{Get the font family name from the font's names table. https://gist.github.com/pklaus/dce37521579513c574d0 r<rz utf-16-bezlatin-1)namesstringr nameIDrr")r?rfamilyFONT_SPECIFIER_NAME_IDFONT_SPECIFIER_FAMILY_IDrecordname_strs rr#zFonts.get_font_family_nameos v!"#$ fo++ &F&--'!==// <!==// :}} 66t"::6! &**622rc|dj}|d}|j}|j}|j}|t |z}||z}t j dk(r<|d}|j} |j} | | z} td|| |z z } | | z} | }n|}tj|}|rd|znd|z}||z S)asCalculate line height ratio based on ``hhea`` and ``OS/2`` tables. Fon non-CJK fonts:: f = (hhea.Ascent - hhea.Descent + hhea.LineGap) / units_per_em For non-CJK fonts (Windows):: f = (OS/2.winAscent + OS/2.winDescent + [External Leading]) / units_per_em External Leading = MAX(0, hhea.LineGap - ((OS/2.WinAscent + OS/2.winDescent) - (hhea.Ascent - hhea.Descent))) For CJK fonts:: f = 1.3 * (hhea.Ascent - hhea.Descent) / units_per_em Read more: * https://docs.microsoft.com/en-us/typography/opentype/spec/recom#baseline-to-baseline-distances * https://github.com/source-foundry/font-line#baseline-to-baseline-distance-calculations * https://www.zhihu.com/question/23349103 * https://github.com/source-foundry/font-line/blob/master/lib/fontline/metrics.py headhheantOS/2gg?g?) unitsPerEmascentdescentlineGapabsosr usWinAscent usWinDescentmaxr is_cjk_font)r? units_per_emrN hhea_ascent hhea_descent hhea_linegaphhea_total_heighthhea_btb_distanceos2os2_win_ascentos2_win_descentos2_win_total_heightwin_external_leadingwin_btb_distance btb_distancecjkdistances rr$zFonts.get_line_height_factors.v11 vkk || || '#l*;;.= 77D=&/C __N!..O#1O#C #&sL:NO`:`,a#b 36JJ +L-L(,/3((S5E,&&rc|d}tjD]&\}}t|ds|jd|zzs&yt jD]\}}|t ddvr"t|ds!|j d|zzs4y|t ddvr%t|dsQ|jd|dz zzsgy|t dd vsxt|d s|jd|dz zzsy |j}|sy tD],}t |d|ddzD]}t||vsy.y #Yy xYw) aTest font object to confirm that it meets our definition of a CJK font file. The definition is met if any of the following conditions are True: 1. The font has a CJK code page bit set in the OS/2 table 2. The font has a CJK Unicode range bit set in the OS/2 table 3. The font has any CJK Unicode code points defined in the cmap table https://github.com/googlefonts/fontbakery/blob/main/Lib/fontbakery/profiles/shared_conditions.py rPulCodePageRange1rBTr @ulCodePageRange2`ulCodePageRange3F) ritemshasattrrkr rangeulUnicodeRange1ulUnicodeRange2ulUnicodeRange3 getBestCmapr int)r?rar0bitcmap unicode_rangexs rrZzFonts.is_cjk_fontsjfo(--/ FAss./C4H4HAQTH4U  -224 FAseArl"3 238K8KqTWx8Xb" %3 238K8KqUXY[U[}8]b" %3 238K8KqUXY[U[}8]  &&(DE/ M=+]1-=a-?@ q6T>   s 6D??EN)__name__ __module__ __qualname____doc__strr classmethodr3 staticmethodr"rrr#r$rZrrrr$s.C&%%P11 >C>> 3V3345'v5'5'p,F,,rr)rrVior collectionsrfontTools.ttLibrcommon.Collectionrcommon.constantsrr r common.sharer r rrrrrsE* "".^^!&+, LNLr