604e889ca4
- spikes/：Word 转 PDF（Gotenberg）、格式识别、原句坐标、DeepSeek 抽取四项验证代码与两版提示词；样本派生产物和 .env 不进 git - tech-validation.md：完整结论。四项都可行：WPS 字体字符集要修正并改用行高调整过的字体；格式识别不需要 Docling；表格内切句待改进；抽取需第三道依据校验与规则兜底 - architecture.md：§3.5 加预处理与字体包，§3.6 证据校验改为三道，§10 回填结论 - 03 功能需求与 decisions.md（TV1）：召回 ≥ 99%、采纳准确率 ≥ 95%、页码 100%、高亮正文 ≥ 98% / 表格 ≥ 95% Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
33 lines
5.4 KiB
XML
33 lines
5.4 KiB
XML
<?xml version="1.0"?>
|
|
<!DOCTYPE fontconfig SYSTEM "fonts.dtd">
|
|
<fontconfig>
|
|
<match target="pattern"><test name="family" qual="any"><string>宋体</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>SimSun</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>新宋体</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>NSimSun</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>仿宋</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>FangSong</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>仿宋_GB2312</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>FangSong_GB2312</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>楷体</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>KaiTi</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>楷体_GB2312</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>KaiTi_GB2312</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>华文楷体</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>华文宋体</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>华文仿宋</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>方正仿宋_GBK</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>方正楷体_GBK</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>方正小标宋简体</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>方正小标宋_GBK</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>方正书宋_GBK</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Serif CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>黑体</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Sans CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>SimHei</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Sans CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>微软雅黑</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Sans CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>Microsoft YaHei</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Sans CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>方正黑体_GBK</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Sans CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>华文黑体</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Sans CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>等线</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Sans CJK SC</string></edit></match>
|
|
<match target="pattern"><test name="family" qual="any"><string>DengXian</string></test><edit name="family" mode="assign" binding="strong"><string>Noto Sans CJK SC</string></edit></match>
|
|
</fontconfig>
|