o e_"@srdZddlZddlmZddlmZddlmZddlm Z ddl m Z m Z m Z ed gd ZGd d d e ZdS) a3Extract 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_RANGESFont descriptorname line_heightc@s~eZdZdZdefddZeddZeddZ ed efd d Z ed e fd dZ ed e fddZ ed e fddZdS)Fontsz$Extracted fonts properties from PDF. font_namecCsb||}|D] }||jkr|Sq|D] }||jvr |Sq|D] }|j|vr.|Sq#dS)z.Get matched font by font name, or return None.N)_to_descriptorr )selfrtargetZfontrCD:\Projects\ConvertPro\env\Lib\site-packages\pdf2docx/font/Fonts.pyget&s z Fonts.getc Cst}|D]}|D] }||dq qg}|D]C}||\}}} } ||} z|dvs3Jdtt| } || } || } Wn t yOd} Ynw| t | | | | dq||S)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/aZcffzbase font or not supported fontNr ) setZ get_fontsaddZ extract_font_normalized_font_namerrget_font_family_nameget_line_height_factor Exceptionappendr r)clsZfitz_docZxrefspagefZfontsZxrefbasenameext_bufferr ttrrrrextract9s*     z Fonts.extractcCs|ddddS)zMNormalize raw font name, e.g. BCDGEE+Calibri-Bold, BCDGEE+Calibri -> Calibri.+-r)splitr rrrr_zFonts._normalized_font_namer cCs|ddddS)zBRemove potential space, dash in font name, and turn to upper case. r))replaceupperr+rrrrer,zFonts._to_descriptortt_fontcCsd}}d}d}|djD]-}d|jvr|jd}n|jd}|j|kr+|s+|}n |j|kr4|s4|}|r:|r:nq t|S)z{Get the font family name from the font's names table. https://gist.github.com/pklaus/dce37521579513c574d0 r.r z utf-16-bezlatin-1)namesstringdecodeZnameIDrr)r1r familyZFONT_SPECIFIER_NAME_IDZFONT_SPECIFIER_FAMILY_IDrecordZname_strrrrrks    zFonts.get_font_family_namecCs|dj}|d}|j}|j}|j}|t|}||}tjdkr?|d}|j} |j} | | } t d|| |} | | } | }n|}t |}|rLd|nd|}||S)a{Calculate 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?) Z unitsPerEmZascentZdescentZlineGapabsosr Z usWinAscentZ usWinDescentmaxr is_cjk_font)r1Z units_per_emr;Z hhea_ascentZ hhea_descentZ hhea_linegapZhhea_total_heightZhhea_btb_distanceos2Zos2_win_ascentZos2_win_descentZos2_win_total_heightZwin_external_leadingZwin_btb_distanceZ btb_distanceZcjkZdistancerrrrs&    zFonts.get_line_height_factorcCs:|d}tD]\}}t|dr|jd|>@rdSqtD]L\}}|tddvr;t|dr:|jd|>@r:dSq |tddvrTt|drS|jd|d>@rSdSq |tdd vrlt|d rl|jd|d>@rldSq z| }WnYd S|s~d St D]}t|d|ddD] }t ||vrdSqqd S) 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 r=ulCodePageRange1r3Tr @ZulCodePageRange2`ZulCodePageRange3F) ritemshasattrrCrrangeZulUnicodeRange1ZulUnicodeRange2ZulUnicodeRange3Z getBestCmapr int)r1rBr#bitZcmapZ unicode_rangexrrrrAs<   zFonts.is_cjk_fontN)__name__ __module__ __qualname____doc__strr classmethodr& staticmethodrrrrrrArrrrr#s % 8r)rPr?ior collectionsrZfontTools.ttLibrZcommon.CollectionrZcommon.constantsrrr r rrrrrs