Digital coding metasurface is a platform connecting the digital space and electromagnetic wave space, and hence has gained extensive attention due to its intriguing value in reshaping wireless channels and realizing new communication architectures. Correspondingly, there is an urgent need for electromagnetic information theory that reveals the capacity bound of communications and supports the accurate design of metasurface-based communication systems. To this end, we propose a macroscopic model and a statistical model of the digital coding metasurface. The macroscopic model uniformly accommodates both digital and electromagnetic aspects of the meta-atoms and predicts all possible scattered fields of the digital coding metasurface based on a small number of simulations or measurements. Full-wave simulations and experimental results show that the macroscopic model is feasible and accurate. A statistical model is further proposed to correlate the mutual coupling between meta-atoms with covariance and to calculate the entropy of the equivalent currents of digital coding metasurface. These two models can help reconfigurable intelligence surfaces achieve more accurate beamforming and channel estimation, and thus improve signal power and coverage. Moreover, the models will promote the design of precoding codebook in metasurface-based direct digital modulation systems to approach the upper bound of channel capacity. In such two models, it is the first time to establish the concepts of current space and current entropy and to analyze the information loss from the coding space to wave space, laying a keystone of bridge that connects the digital world and the physical world, and advancing developments of electromagnetic information theory and new-architecture wireless systems.